Home

Manikanta reddy Kasam - Sr. AI/ML Engineer

[email protected]

Location: Dallas, Texas, USA

Relocation:

Visa: GC

Resume file: MANIKANTA RESUME..'_1781533576762.docx Please check the file(s) for viruses. Files are checked manually and then made available for download.

MANIKANTA K Senior AI/ML Engineer | LLM & RAG Specialist | Generative AI (469) 708-7552 [email protected] github.com/Manikantakasam0127 https://scintillating-dasik-aa3171.netlify.app/ PROFESSIONAL SUMMARY I've been working in ML and data science for about 11 years now, and the last couple of years have been mostly focused on LLMs and Generative AI in production. My background started in classical ML churn models, fraud detection, NLP pipelines and I moved into RAG systems and agentic AI as the tooling matured around 2023. Right now at Fifth Third Bank I'm building RAG pipelines, LangGraph-based agentic workflows, and LLM evaluation frameworks that run at enterprise scale. I also use AWS GenAI tools like Amazon Bedrock, Amazon Q, and Kiro for SDLC transformation and developer productivity helping engineering teams adopt agentic workflows and AI-assisted development practices. Before that I was at Tailored Brands doing a mix of traditional ML and early LLM integration from mid-2023. I'm comfortable across the full stack from feature engineering and model training to API deployment, monitoring, and drift detection. I've worked in regulated environments, mentored junior engineers, and know how to explain model outputs to people who don't write code. CORE COMPETENCIES LLM Integration (GPT-4o, LLaMA 3, Mistral) | LlamaIndex | AutoGen | RAG Pipelines | Graph RAG | Agentic AI | LangChain | LangGraph (2024+) | LangSmith | Azure OpenAI | AWS Bedrock | Amazon Q | Kiro (AWS SDLC AI) | MCP Server Integration | Prompt Engineering | Chain-of-Thought Prompting | Vector Databases (FAISS, Pinecone, Weaviate) | Hybrid Search | RAGAS Evaluation | NLP & Transformers | BERT | Hugging Face | MLOps | LLMOps | CI/CD for AI | Model Monitoring | Drift Detection | SHAP | LIME | Responsible AI | GDPR & CCPA Compliance TECHNICAL SKILLS LLMs & Gen AI GPT-4/GPT-4o, Azure OpenAI API, OpenAI API, AWS Bedrock, Amazon Q, Amazon Q Developer, Kiro (AWS SDLC AI Tool), LLaMA 3, Mistral, Claude API, Prompt Engineering, Chain-of-Thought, Few-shot Prompting, Structured Output (JSON mode), Context Engineering, Token Optimization AWS GenAI Tools Amazon Bedrock (Claude, LLaMA, Titan, Nova), Amazon Q (Business, Developer), Kiro (Spec-first AI coding), Amazon SageMaker, AWS Lambda AI, Amazon Textract, Amazon Comprehend, Amazon Lex, MCP Server Integration Agentic AI LangChain, LangGraph (2024+), LlamaIndex, AutoGen, CrewAI, MCP (Model Context Protocol), Agentic Workflows, ReAct Pattern, Multi-agent Systems, Tool Orchestration, Function Calling, LangSmith, SDLC Transformation with AI RAG & Vector Search RAG Pipelines, Graph RAG, FAISS, Pinecone, Weaviate, Qdrant, Chroma, Hybrid Search (BM25 + Dense Vector), Re-ranking (Cohere, CrossEncoder), Sentence-Transformers, RAGAS, LLM-as-Judge, Contextual Compression, Chunking Strategies NLP & Transformers BERT, RoBERTa, Hugging Face Transformers, Sentence-Transformers, BERTopic, spaCy, NLTK, Sentiment Analysis, Text Classification, NER, Zero-shot Classification ML / DL Scikit-learn, TensorFlow, PyTorch, XGBoost, LightGBM, CatBoost, Isolation Forest, Autoencoders, LSTM, ARIMA, Prophet, Optuna, SMOTE/ADASYN MLOps / LLMOps MLflow, Kubeflow, Apache Airflow, Docker, Kubernetes, Jenkins, GitHub Actions, Weights & Biases, Evidently AI, DVC, Canary Releases, Shadow Deployment, Model Registry, Feature Stores Cloud Azure (ML Studio, Databricks, OpenAI, AI Foundry, Data Factory, AKS), AWS (SageMaker, Bedrock, Amazon Q, EC2, Lambda, S3, Glue, EKS), GCP (BigQuery, Vertex AI) APIs & Services FastAPI, Flask, REST APIs, GraphQL, gRPC, Streaming APIs, Microservices, Real-time & Batch Inference Big Data Apache Spark, PySpark, Kafka, Delta Lake, Apache Iceberg, AWS Glue, Databricks, dbt, Hadoop Programming Python (Expert), SQL, R, Scala, PySpark, TypeScript, Bash Databases MongoDB, PostgreSQL, MySQL, Cassandra, Neo4j, Snowflake, Redshift, Redis, Elasticsearch, Pinecone WORK EXPERIENCE Senior AI/ML Engineer Jul 2025 Present Fifth Third Bank Cincinnati, OH Built production RAG pipeline using Azure OpenAI (GPT-4o) and FAISS with hybrid BM25 + dense retrieval and Cohere re-ranking running across 1M+ daily customer interactions with 35% reduction in support resolution time. Landed on parent-child chunking after testing fixed-size and sentence-window approaches. Built Graph RAG using Neo4j knowledge graphs and LangChain to ground LLM responses in structured facts hallucination rates dropped 23% measured using RAGAS faithfulness scores with LLM-as-Judge. Integrated Amazon Q Developer and Kiro into the SDLC workflow using Kiro's spec-first approach to validate requirement documentation, auto-generate JIRA stories, and define coding standards and architectural constraints as AI agent rules files, cutting requirement gathering time by 40%. Used Amazon Bedrock alongside Azure OpenAI evaluated Claude, LLaMA 3, and Amazon Nova models for different financial services use cases based on cost, latency, and accuracy. MCP server integrations enabled standardized tool-calling across model providers. Designed agentic workflows in LangGraph (from early 2024) with ReAct reasoning across internal banking systems added human-in-the-loop checkpoints at critical decision nodes and removed about 60% of manual analyst steps daily. Prompt engineering chain-of-thought, few-shot examples, structured JSON output. Response accuracy improved around 28% and token costs came down about 25% at scale across millions of LLM calls per day. Set up LLMOps stack LangSmith for tracing and prompt versioning, RAGAS for quality scoring, Evidently AI for drift, W&B for experiments, MLflow as model registry. Automated retraining cut model degradation incidents by around 80%. CI/CD for model releases via GitHub Actions and Jenkins automated pytest, Docker builds, canary deployments on Kubernetes. Deployment errors dropped to zero and release cycle shortened by about 38%. Delivered churn prediction system using XGBoost with Optuna tuning and SHAP dashboards 23% churn reduction and roughly $5M in annual retention revenue. Stack: Python, Azure OpenAI (GPT-4o), Amazon Bedrock, Amazon Q Developer, Kiro, LangChain, LangGraph (2024+), LlamaIndex, AutoGen, MCP, FAISS, Pinecone, Neo4j, Graph RAG, RAGAS, LangSmith, BERT, XGBoost, TensorFlow, PyTorch, SHAP, MLflow, W&B, Evidently AI, Docker, Kubernetes, GitHub Actions, Jenkins, AWS (SageMaker, S3, Glue, Lambda, EKS), Azure (ML, AKS, Databricks, AI Foundry), FastAPI, PostgreSQL, MongoDB AI/ML Engineer Apr 2023 Jun 2025 Tailored Brands Fremont, CA Built fraud detection system using Isolation Forest and Autoencoders in ensemble, deployed as real-time REST API on Azure ML fraudulent transactions dropped 35%, saved about $2M annually. Added SHAP outputs for compliance reporting. Built LangChain prompt pipelines and RAG system using Pinecone for product knowledge retrieval handling around 65% of tier-1 support without agent involvement by the time I left. Search relevance improved 41%, zero-result queries dropped 44%. Integrated Amazon Q Business for internal knowledge management enabling teams to query product documentation and operational runbooks in natural language. Used Amazon Bedrock to evaluate multiple foundation models for cost-efficiency across different task types. Demand forecasting using ARIMA, LSTM, and Prophet tuned with Optuna planning accuracy up 18%, inventory costs down 15%, stockouts dropped 19%. Customer segmentation with K-Means and DBSCAN clustering enabled targeted campaigns that converted 22% better than untargeted. The marketing team used this directly for campaign planning. Full MLOps lifecycle Evidently AI for drift, W&B for tracking, DVC for data versioning, GitHub Actions CI/CD, canary rollouts. Model reliability stayed above 99.5% throughout. ETL optimization using PySpark, Azure Databricks, and Delta Lake with dbt processing time dropped from about 2 hours to 27 minutes end to end. Dynamic pricing engine using reinforcement learning and Bayesian optimization via FastAPI e-commerce revenue up 10%, roughly $3M annually. Mentored five data scientists on MLOps and Azure ML deployment patterns. Stack: Python, Azure OpenAI (GPT-4), Amazon Bedrock, Amazon Q Business, LangChain, Pinecone, FAISS, Azure ML, Azure Databricks, Delta Lake, dbt, PySpark, Kafka, MLflow, W&B, Evidently AI, GitHub Actions, Docker, Kubernetes, XGBoost, TensorFlow, PyTorch, SHAP, MongoDB, MySQL Data Scientist Nov 2020 Mar 2023 Charter Communications Maryland Heights, MO Built churn prediction system using XGBoost on AWS SageMaker at 85% accuracy with SHAP-driven feature analysis retained around $2M in annual subscription revenue with Evidently AI drift monitoring and automated retraining. NLP ticket classification using BERT and RoBERTa auto-categorized 50K+ monthly support tickets. Improved response times by 20%, CSAT up 15 points. Recommendation system using collaborative filtering on SageMaker increasing average order value by 12%, generating $1.5M annually. Real-time anomaly detection on IoT sensor data using Isolation Forest Grafana and Prometheus dashboards for monitoring, reduced downtime by 19% and saved ~$800K annually. Containerized ML model serving via Docker with Jenkins CI/CD cut experiment-to-deployment time by 30%. Stack: Python, AWS (SageMaker, S3, EC2), Scikit-learn, XGBoost, TensorFlow, PyTorch, BERT, RoBERTa, Hugging Face, SHAP, MLflow, Evidently AI, Grafana, Prometheus, Docker, Jenkins, Airflow, PostgreSQL, MySQL, Tableau, Power BI Data Analyst Jan 2019 Oct 2020 Change Healthcare Nashville, TN Analyzed 2M+ consumer records using Python and SQL surfacing patterns contributing to 12% revenue growth across 5 business units. Built sales forecasting models at 88% accuracy, automated recurring reporting saving 10+ hours per week, and designed Tableau and Power BI dashboards tracking 25+ KPIs for leadership. Implemented data governance policies and quality audits achieving 100% compliance and reducing data quality incidents by 40%. Stack: Python, SQL, R, Tableau, Power BI, Excel, Scikit-learn, MySQL, PostgreSQL, AWS (S3, EC2), Matplotlib, Seaborn Junior Data Analyst Jun 2015 Aug 2018 RedPine Solutions Hyderabad, India Built SQL queries and data models for BI reporting across 10+ business units improved reporting accuracy by 30%. Automated data processing using Python and VBA cut manual prep by 8 hours per week. Stack: Python, SQL, Tableau, Excel, VBA, MySQL, PostgreSQL, Git, AWS EDUCATION Bachelor of Technology, Computer Science 2010 2014 CMR College of Engineering & Technology Keywords: continuous integration continuous deployment artificial intelligence machine learning business intelligence sthree rlang trade national California Missouri Ohio Tennessee