Home

Ravichandran Gokul - Lead AI/ML Engineer

[email protected]

Location: Terre Haute, Indiana, USA

Relocation: YES

Visa: USC

Resume file: Ravichandran Gokul_1780925732108.docx Please check the file(s) for viruses. Files are checked manually and then made available for download.

Ravichandran Gokul Lead AI/ML Engineer Email: [email protected] Contact: +1 (512) 814-5685 Professional Overview Lead AI/ML Engineer with 12+ years of experience designing, architecting, and delivering enterprise-scale Artificial Intelligence, Machine Learning, Generative AI, Agentic AI, and Data Engineering solutions across Banking, Healthcare, Life Sciences, Telecommunications, and Manufacturing domains. Proven expertise in building Financial Crime Intelligence platforms, AML/KYC solutions, Fraud Detection systems, Trade Surveillance platforms, Clinical Documentation Integrity (CDI) solutions, Population Health Analytics platforms, Drug Discovery analytics, and Customer 360 ecosystems. Extensive experience developing enterprise Generative AI and Agentic AI solutions using GPT-4o, Claude, Llama, OpenAI, Amazon Bedrock, LangChain, LangGraph, CrewAI, RAG, Semantic Search, AI Copilots, and Knowledge Graph architectures. Strong hands-on expertise in designing cloud-native AI and analytics platforms across AWS, Azure, and GCP leveraging SageMaker, Azure ML, Vertex AI, Databricks, Snowflake, Spark, Kafka, Kubernetes, and Terraform. Experienced in architecting scalable Data Lakehouse, ETL/ELT, real-time streaming, and enterprise data engineering solutions supporting large-scale structured and unstructured data processing. Skilled in developing intelligent document processing, semantic search, enterprise knowledge management, and decision-support systems using vector databases, embeddings, and advanced retrieval frameworks. Hands-on experience building scalable microservices and AI platforms using Python, Java, PySpark, SQL, FastAPI, Spring Boot, REST APIs, Docker, and Kubernetes. Expertise in Machine Learning, Deep Learning, NLP, Predictive Analytics, Recommendation Systems, Time-Series Forecasting, Entity Resolution, Graph Analytics, and Explainable AI solutions. Proven track record implementing enterprise MLOps and LLMOps frameworks using MLflow, Kubeflow, LangSmith, CI/CD pipelines, GitHub Actions, Jenkins, Terraform, and Infrastructure-as-Code practices. Experienced in deploying secure, production-grade AI solutions incorporating RBAC, IAM, encryption, audit logging, PII/PHI protection, model monitoring, and enterprise security controls. Strong knowledge of Data Governance, Model Governance, Responsible AI, AI Security, Observability, Data Quality, Metadata Management, and Regulatory Compliance frameworks. Adept at collaborating with executive leadership, business stakeholders, clinicians, compliance teams, architects, and engineering organizations to deliver scalable AI-driven solutions that improve operational efficiency, accelerate decision-making, strengthen regulatory compliance, and drive measurable business value. Technical Skills Category Technologies PROGRAMMING Python, Java, SQL, PySpark, R, Shell Scripting GENERATIVE AI & AGENTIC AI GPT-4o, OpenAI, Claude, Llama 3, Amazon Bedrock, Azure OpenAI, CrewAI, LangChain, LangGraph, Agentic AI, RAG, Prompt Engineering, Fine-Tuning (LoRA, PEFT, SFT) MACHINE LEARNING & NLP Scikit-Learn, TensorFlow, PyTorch, XGBoost, LightGBM, CatBoost, FinBERT, ClinicalBERT, BioBERT, Med-BERT, Transformers VECTOR DB & KNOWLEDGE GRAPHS Pinecone, FAISS, Databricks Vector Search, Neo4j, Amazon Neptune, Graph Data Science CLOUD PLATFORMS AWS (Bedrock, SageMaker, S3, EMR, Glue, Redshift, Lambda, EKS), Azure (Databricks, Azure ML, Azure OpenAI, ADF, ADLS), GCP (Vertex AI, BigQuery, Dataproc, Dataflow, GCS) DATA ENGINEERING Databricks, Delta Lake, Snowflake, Spark, Kafka, Hadoop, Hive, ETL/ELT, Data Lakehouse MLOPS & LLMOPS MLflow, Kubeflow, LangSmith, Prompt Flow, Docker, Kubernetes, Terraform, Jenkins, GitHub Actions, CI/CD OBSERVABILITY & GOVERNANCE Prometheus, Grafana, OpenTelemetry, CloudWatch, Purview, Unity Catalog, Collibra, Great Expectations, Data Governance BACKEND DEVELOPMENT FastAPI, Spring Boot, Flask, REST APIs, Microservices VISUALIZATION Tableau, Power BI, AWS QuickSight HEALTHCARE DOMAIN FHIR, HL7, HIPAA, CDI, Clinical NLP, Population Health Analytics BANKING DOMAIN AML, KYC, Fraud Detection, Trade Surveillance, Customer 360, Basel III, CCAR, OCC, FFIEC, SR 11-7 LIFE SCIENCES Pharmacovigilance, MedDRA, Drug Discovery, Clinical Trials, RWE, GxP CORE EXPERTISE Generative AI, Agentic AI, Knowledge Graphs, Fraud Analytics, Clinical Analytics, Predictive Modeling, Data Governance, Responsible AI, Explainable AI (SHAP, LIME, Fairlearn) Professional Experience Lead AI/ML Engineer BANK OF AMERICA, Charlotte (NC) (Remote) (Jan 2023 Present) Led enterprise AI, Generative AI, and Machine Learning initiatives supporting Financial Crime Intelligence, AML, KYC, Fraud Detection, Trade Surveillance, Regulatory Compliance, Wealth Management, and Customer programs across Bank of America. Architected a unified Financial Crime Intelligence platform integrating AML monitoring, sanctions screening, customer due diligence, fraud analytics, adverse media intelligence, and suspicious activity investigations. Designed and implemented Agentic AI and multi-agent solutions using GPT-4o, OpenAI, Claude, Amazon Bedrock, CrewAI, LangGraph, and LangChain to automate compliance investigations, alert triage, regulatory research, and analyst workflows. Built enterprise RAG and semantic search platforms leveraging OpenAI embeddings, Pinecone, Neo4j, OpenSearch, Databricks Vector Search, and Knowledge Graphs to deliver grounded and explainable responses across regulatory and operational knowledge repositories. Developed a GenAI-powered Compliance & Risk Copilot enabling auditors, compliance teams, and risk analysts to interact with OCC, FFIEC, Basel III, CCAR, and SR 11-7 policies using natural language interfaces. Led development of Market Surveillance and Trading Intelligence solutions supporting trade monitoring, insider trading detection, market abuse investigations, transaction surveillance, and behavioral risk analytics. Developed AML, fraud detection, and trade surveillance models using XGBoost, LightGBM, CatBoost, Isolation Forest, Deep Learning, and Graph Neural Networks to improve detection accuracy and reduce false positives. Built graph-based entity resolution and relationship intelligence platforms using Neo4j, Amazon Neptune, Graph Data Science, GraphSAGE, and NetworkX to uncover connections among customers, accounts, merchants, traders, and counterparties. Designed enterprise Customer 360 architecture integrating deposits, lending, wealth management, CRM, digital banking, and trading datasets into a unified customer intelligence platform. Developed AI-powered Banker, Advisor, and Relationship Manager Copilots delivering portfolio insights, client intelligence, next-best-action recommendations, and personalized engagement strategies. Built NLP and document intelligence pipelines using FinBERT, RoBERTa, DeBERTa, GPT-4o, OCR, and fine-tuned LLaMA models to process regulatory filings, audit reports, research documents, customer communications, and trading records. Implemented supervised fine-tuning (SFT), LoRA, PEFT, prompt engineering, and domain adaptation techniques to improve financial reasoning, compliance understanding, and GenAI response quality. Designed scalable ETL/ELT and real-time data pipelines using Python, Java, SQL, PySpark, Kafka, Databricks, Snowflake, AWS Glue, Delta Lake, and Spark Structured Streaming processing millions of daily transactions. Established enterprise data governance, lineage, reconciliation, metadata management, and data quality frameworks using Collibra, Unity Catalog, AWS Glue Data Catalog, and automated validation pipelines. Developed cloud-native AI microservices and APIs using Python, FastAPI, Java, Spring Boot, Docker, Kubernetes, and REST services supporting enterprise AI application integration. Implemented enterprise MLOps and LLMOps platforms using SageMaker, MLflow, Kubeflow, LangSmith, GitHub Actions, Jenkins, Terraform, Docker, and Kubernetes to automate model lifecycle management and production deployments. Established CI/CD, observability, and AI monitoring frameworks using CloudWatch, Prometheus, Grafana, OpenTelemetry, and LangSmith to improve reliability, governance, and operational visibility. Led Responsible AI, Model Governance, Explainable AI, and compliance initiatives utilizing SHAP, LIME, Fairlearn, model validation frameworks, and regulatory controls aligned with OCC, FFIEC, Basel III, CCAR, and SR 11-7 standards. Implemented secure GenAI architectures incorporating PII masking, IAM, RBAC, encryption, Secrets Manager, audit logging, prompt security, jailbreak detection, and enterprise AI guardrails. Led migration of legacy SAS, Teradata, Oracle, and Hadoop platforms to Snowflake, Databricks Lakehouse, and AWS-native analytics ecosystems while mentoring AI/ML, Data Engineering, and platform teams on Agentic AI, RAG, Knowledge Graphs, Data Governance, and cloud-native AI engineering. Environment: AWS (Amazon Bedrock, SageMaker, S3, EMR, Glue, Athena, Redshift, OpenSearch, Lambda, Kinesis, DynamoDB, IAM, KMS, CloudWatch, Secrets Manager, EKS), Python, Java, Spring Boot, FastAPI, SQL, PySpark, Databricks, Delta Lake, Snowflake, Kafka, OpenAI, GPT-4o, Claude, Llama 3, CrewAI, LangChain, LangGraph, Pinecone, Neo4j, Amazon Neptune, MLflow, LangSmith, Prompt Flow, Kubeflow, Docker, Kubernetes, Terraform, Jenkins, GitHub Actions, SHAP, LIME, Fairlearn, FinBERT, XGBoost, LightGBM, CatBoost, Basel III, CCAR, AML, KYC, SR 11-7, OCC, FFIEC, Customer 360, Trade Surveillance, Fraud Analytics, Data Governance. Senior AI/ML Engineer HCA HEALTHCARE, Nashville, (TN) (Jan 2020 Dec 2022) Led enterprise AI/ML, Clinical NLP, and healthcare analytics initiatives supporting Clinical Documentation Integrity (CDI), Population Health, Care Management, Patient Engagement, and Operational Intelligence across multi-hospital networks. Architected a hybrid Azure-GCP healthcare lakehouse platform integrating EHR, EMR, FHIR, HL7, claims, pharmacy, radiology, and laboratory data using Azure Databricks, Delta Lake, BigQuery, Snowflake, ADLS, and GCS. Designed and delivered a Clinical Documentation Integrity (CDI) platform automating documentation gap detection, DRG optimization, coding assistance, and provider query recommendations. Built physician copilots and clinical intelligence solutions for chart summarization, diagnosis validation, clinical coding, discharge planning, and treatment guidance. Engineered large-scale ETL/ELT pipelines using Azure Data Factory, Databricks, PySpark, SQL, BigQuery, and Cloud Composer processing billions of healthcare records. Developed advanced Clinical NLP solutions using ClinicalBERT, BioBERT, Med-BERT, TensorFlow, PyTorch, and Azure Cognitive Services for clinical concept extraction and medical coding automation. Implemented document intelligence frameworks using Azure Form Recognizer, OCR, NLP, and metadata extraction to process pathology reports, physician notes, and clinical documents. Built predictive models for patient readmission, risk stratification, chronic disease management, and value-based care using XGBoost, Random Forest, Neural Networks, and Spark MLlib. Developed care recommendation and next-best-action models improving patient outreach, treatment adherence, and preventive care initiatives. Designed semantic search and clinical knowledge retrieval platforms using Azure Cognitive Search, Pinecone, FAISS, vector embeddings, and healthcare ontologies. Architected healthcare Knowledge Graph solutions integrating patients, providers, diagnoses, medications, encounters, and care pathways for clinical analytics and decision support. Developed cloud-native AI microservices using Python, FastAPI, Java, Spring Boot, REST APIs, Azure Functions, and event-driven architectures. Implemented real-time healthcare analytics using Kafka, Event Hubs, Pub/Sub, Spark Structured Streaming, and Databricks Streaming for operational and patient-event monitoring. Built reusable healthcare Feature Store frameworks supporting patient, provider, utilization, and clinical features across multiple ML initiatives. Led MLOps implementation using Azure ML, Vertex AI, MLflow, Kubeflow, Docker, Kubernetes, Terraform, Jenkins, and GitHub Actions for model deployment and lifecycle management. Established CI/CD pipelines, model monitoring, observability, and drift detection using Prometheus, Grafana, OpenTelemetry, Azure Monitor, and Cloud Monitoring. Implemented HIPAA-compliant security, PHI masking, RBAC, IAM, Key Vault, Secret Manager, audit logging, and governance controls. Developed enterprise data governance and quality frameworks using Purview, Unity Catalog, Dataplex, Great Expectations, lineage tracking, and metadata management. Optimized Databricks, Spark, BigQuery, and Snowflake workloads through partitioning, caching, Delta optimization, clustering, and query tuning. Evaluated early Generative AI and Azure OpenAI healthcare use cases for clinical knowledge retrieval, question answering, and physician-assist workflows while mentoring teams on healthcare AI, MLOps, interoperability, and Responsible AI practices. Environment: Azure Databricks, Azure Data Factory, Azure ML, Azure OpenAI, Azure Cognitive Search, ADLS, Event Hubs, Vertex AI, BigQuery, GCS, Pub/Sub, Python, PySpark, SQL, Java, Spring Boot, FastAPI, TensorFlow, PyTorch, ClinicalBERT, BioBERT, Med-BERT, XGBoost, Pinecone, FAISS, Snowflake, Kafka, Spark Streaming, MLflow, Kubeflow, Docker, Kubernetes (AKS/GKE), Terraform, Jenkins, GitHub Actions, Prometheus, Grafana, OpenTelemetry, Purview, Unity Catalog, Dataplex, Great Expectations, FHIR, HL7, HIPAA, Data Governance, Tableau, Power BI. Machine Learning Engineer ELI LILLY & COMPANY, Indianapolis (IN) (Jan 2017 Dec 2019) Developed enterprise Machine Learning and advanced analytics solutions supporting Clinical Development, Drug Discovery, Pharmacovigilance, Real-World Evidence (RWE), and Regulatory Operations across multiple therapeutic areas. Architected GCP-based clinical analytics platforms using BigQuery, Dataproc, Dataflow, Cloud Storage, and Pub/Sub to process large-scale clinical, patient, and safety datasets. Built predictive models for clinical trial enrollment forecasting, patient recruitment optimization, site selection, investigator performance analysis, and patient retention. Designed scalable ETL/ELT pipelines using Python, PySpark, SQL, Hadoop, Hive, Informatica, and BigQuery integrating data from EDC, CTMS, EHR, laboratory, and safety systems. Developed pharmacovigilance analytics platforms for adverse event monitoring, safety signal detection, case prioritization, and regulatory reporting. Built NLP solutions using TensorFlow, Bi-LSTM, CRF, and early transformer models for clinical concept extraction, adverse event identification, and medical coding automation. Implemented entity recognition, relationship extraction, and document intelligence solutions processing clinical study reports, protocols, investigator brochures, and regulatory submissions. Developed patient cohort identification, protocol feasibility, and precision medicine models supporting biomarker-driven studies and targeted recruitment. Built recommendation engines for optimal clinical trial site selection using enrollment history, investigator productivity, and demographic analytics. Developed ML models for drug efficacy prediction, patient outcome analysis, compound screening, and molecular property prediction using deep learning techniques. Implemented distributed ML workloads using Spark MLlib, Hadoop, TensorFlow, H2O.ai, and Scikit-Learn processing terabytes of clinical and research data. Built forecasting models supporting clinical supply chain planning, investigational drug demand forecasting, and inventory optimization initiatives. Established ML experimentation, model validation, and monitoring frameworks using MLflow, TensorFlow, H2O.ai, and Scikit-Learn to improve reproducibility and governance. Developed REST APIs and Flask-based microservices exposing predictive analytics solutions to clinical and operational applications. Built executive dashboards and self-service analytics solutions using Tableau, Power BI, SQL, and BigQuery while ensuring GxP, FDA, and regulatory compliance across analytics environments. Collaborated with clinical scientists, biostatisticians, safety teams, and regulatory stakeholders to operationalize ML solutions and modernize legacy SAS-based analytics platforms on GCP. Environment: GCP (BigQuery, Dataproc, Dataflow, Cloud Storage, Cloud Composer, Pub/Sub), Python, PySpark, SQL, Spark, Hadoop, Hive, HDFS, TensorFlow, Keras, Scikit-Learn, H2O.ai, MLflow, Informatica, Flask, REST APIs, BigQuery ML, Oracle, Tableau, Power BI, MedDRA, WHO Drug, Pharmacovigilance, Drug Discovery, Clinical Trial Analytics, RWE, GxP Compliance. Senior Data Scientist AT&T, Dallas (TX) (Jan 2015 Dec 2016) Led advanced analytics initiatives supporting subscriber retention, customer experience optimization, network performance management, revenue growth, and telecom fraud prevention across wireless and broadband business units. Developed enterprise churn prediction and customer propensity models using Python, R, Scikit-Learn, XGBoost, Random Forest, and Gradient Boosting to identify retention risks and improve customer loyalty. Built Customer 360 analytical platforms integrating CRM, billing, usage, call detail records (CDR), service tickets, and digital interaction datasets to provide a unified subscriber view. Designed customer segmentation and recommendation engines supporting personalized offers, service upgrades, cross-sell opportunities, and targeted marketing campaigns. Developed large-scale ETL and data processing pipelines using Hadoop, Hive, Pig, Spark, SQL Server, AWS S3, and EMR to process billions of telecom events and customer transactions. Built predictive models identifying service cancellation risks, payment delinquency patterns, customer dissatisfaction indicators, and subscription fraud activities. Developed NLP and sentiment analysis solutions using Python and TensorFlow to analyze customer feedback, surveys, complaints, emails, and social media interactions. Created network analytics platforms identifying congestion hotspots, dropped-call trends, outage risks, and service degradation patterns using operational and telemetry datasets. Built time-series forecasting models for bandwidth utilization, network demand forecasting, infrastructure planning, and capacity optimization. Designed geospatial analytics solutions supporting network expansion planning, tower placement optimization, market penetration analysis, and coverage improvement initiatives. Developed executive dashboards and operational intelligence reporting solutions using Tableau, Power BI, AWS QuickSight, and SQL-based reporting frameworks. Deployed machine learning solutions through Python APIs, REST services, and AWS-hosted analytics platforms while collaborating with marketing, customer care, network engineering, and business leadership teams. Environment: AWS (S3, EMR, EC2, Redshift, QuickSight), Python, R, SQL, Spark, Hadoop, Hive, Pig, HDFS, Oozie, Scikit-Learn, XGBoost, TensorFlow, SQL Server, Tableau, Power BI, REST APIs, Linux, Shell Scripting, Customer 360, Churn Analytics, Fraud Detection, Network Analytics. Data Scientist / Data Analyst INTEL CORPORATION, Schaumburg (IL) (Jan 2014 Dec 2015) Developed advanced manufacturing analytics solutions supporting semiconductor fabrication, yield optimization, equipment reliability, quality engineering, and production efficiency initiatives. Built predictive maintenance models using Python, R, and machine learning algorithms to forecast equipment failures and reduce unplanned downtime across fabrication facilities. Performed exploratory data analysis and root-cause investigations to identify process bottlenecks, defect drivers, and manufacturing inefficiencies. Developed statistical process control (SPC), anomaly detection, and yield optimization models to improve wafer manufacturing performance and reduce defect rates. Designed time-series forecasting solutions using high-frequency sensor data to optimize maintenance schedules and production planning. Built large-scale data processing and ETL pipelines using SQL, Hadoop, Hive, HDFS, and AWS S3 to support manufacturing analytics and engineering operations. Implemented clustering, segmentation, regression, and multivariate statistical models to identify equipment utilization trends and process performance variations. Created interactive Tableau dashboards and KPI reporting solutions providing operational insights to engineering, quality, and manufacturing leadership teams. Collaborated with process engineers and manufacturing teams to deliver data-driven recommendations that improved yield, throughput, and operational performance. Automated reporting workflows and supported migration of analytics workloads into Hadoop and AWS-based big data environments, improving scalability and reporting efficiency. Environment: AWS (S3, EC2, EMR), Python, R, SQL, Hadoop, Hive, HDFS, Tableau, Excel, SAS, Statistical Modeling, Predictive Maintenance, Manufacturing Analytics, Yield Optimization, Time-Series Analysis, Regression, ANOVA, Clustering, ETL, Linux. Education: Master of Science in Computer Science | Indiana State University (Terre Haute, IN) Bachelor of Engineering in Computer Science |MSEC, Anna University (Tamilnadu, India) Keywords: continuous integration continuous deployment artificial intelligence machine learning business intelligence sthree database rlang trade national Illinois North Carolina Tennessee Texas