Home

chaitanya yadlapalli - Python developer, AI Engineer, ML Engineer, Gen AI Engineer, Agentic AI Engineer, Machine Learning Engineer, Lead AI Engineer, Lead Data

[email protected]

Location: Remote, Remote, USA

Relocation: yes

Visa: H1b

Resume file: Chaitanya_Yadlapalli_Resume_1777915959442.docx Please check the file(s) for viruses. Files are checked manually and then made available for download.

Chaitanya Yadlapalli Lead AI/ML Engineer | GenAI & Agentic Systems Architect [email protected] | +1 (240) 7398-945 | www.linkedin.com/in/chaitanya20/ Professional Summary: AI Engineer with deep hands-on experience in agentic workflows, RAG pipelines, and API-driven automation. Skilled in building LLM-powered agents capable of reasoning, tool usage, and multi-system collaboration. Strong expertise in Python, LangChain, AutoGen, vector databases, and AI-driven development platforms like Cursor AI. Focused on delivering scalable intelligent systems that integrate seamlessly with products and engineering workflows. 10+ years of experience in data engineering, machine learning model development, data warehousing, and analytical solution design, with deep expertise in data collection, transformation, and integration. Strong adaptability to emerging AI trends, integrating Large Language Models (LLMs) and Agentic AI frameworks to build autonomous, intelligent data-driven systems. Collaborative problem solver, experienced in engaging with stakeholders, business users, and SMEs to translate complex business requirements into scalable technical solutions. Hands-on experience with Azure Data Lake, Azure Cognitive Services, Azure OpenAI, Cosmos DB, AKS, and Azure Functions Experience building RAG pipelines, LLM fine-tuning, NLP pipelines, and autonomous agent platforms using LangChain/LangGraph Strong focus on model governance, data privacy, responsible AI practices, and secure cloud deployment Technically proficient in SQL, Python, Apache Airflow, NiFi, RESTful APIs, and AI security tools (Joe Security API, VirusTotal, YARA, YOLO Models, HDFS). Certified in Software Engineering for Data Science, with a strong foundation in cloud technologies (AWS, Azure), data pipelines, ML deployment, and best practices for scalability and security. Specialized in building multi-agent systems using Crew.AI and LangGraph for autonomous data workflows and SQL agent orchestration. Experienced in cloud and DevOps workflows, including hybrid deployments, CI/CD automation, model monitoring, and system observability. Crew.AI, AutoGen, and LangGraph for multi-agent coordination. Fine-tuning and optimizing foundation models for enterprise GenAI applications. Leadership & mentorship experience driving cross-functional collaboration and guiding junior engineers in data and AI initiatives. Skilled in API strategy and integration, developing APIs as key acquisition and interoperability channels. Agile and Scrum practitioner, ensuring structured, efficient, and timely project execution. Excellent communication and client engagement skills, adept at coordinating global teams and delivering high- quality outcomes in fast-paced environments. TECHNICAL SKILLS: LLM & Agentic AI LangChain, LangGraph, RAG Pipelines, Vector DBs (Pinecone, FAISS, Qdrant), OpenAI APIs, Azure OpenAI, Crew.AI, AutoGen Distributed Systems Kafka, Kubernetes, FastAPI, Docker, Microservices, AKS, Azure Functions, API Gateway Cloud Platforms Azure (primary), AWS, Databricks Azure Ecosystem Azure OpenAI, Cosmos DB, Cognitive Services, Azure Data Lake, AI Search, Azure Functions, AKS, ACR, Azure Monitor, Synapse (hands-on exposure), Microsoft Fabric (familiarity) ML & DL Scikit-learn, TensorFlow, PyTorch, XGBoost, Timeseries modeling Observability & ML Arize AX, LangFuse, CloudWatch, X-Ray, Azure Monitor, Responsible AI practices, AI ethics & governance Professional Experience Client: HSBC Bank February 2024 Present Role: Lead Gen AI Engineer Led architecture and delivery of a multi-agent orchestration platform using Azure OpenAI, LangGraph, and AKS, enabling low-code design, deployment, and monitoring of autonomous agents across distributed environments. Responsibilities: Led development of multi-agent orchestration using LangGraph, Claude Models, and Azure OpenAI for adaptive reasoning. Designed adaptive reasoning frameworks powered by LLMs and SML, integrating LangGraph, Claude, and Titan models for task decomposition and decision automation. Implemented agentic workflows using Azure Functions, Cosmos DB, and Azure AI Search with vector indexing for contextual retrieval and persistence. Developed SQL Agent using Azure SQL Database and LangGraph, enabling natural language querying over structured data. Orchestrated multi-LLM routing across Azure OpenAI and Amazon Bedrock, optimizing agent performance based on contextual metrics. Applied observability with Azure Monitor, OpenTelemetry, and Datadog for latency tracking, drift detection, and system health. Reduced agent deployment time by 60% through reusable orchestration modules and standardized delivery frameworks. Directed end-to-end execution across 8-member engineering teams, aligning AI architecture, infrastructure, and production readiness with TPOs and TPMs. Established enterprise-grade review and observability standards using LangFuse, Azure DevOps, and ARM templates. Delivered agentic AI pipelines from ingestion to deployment using Azure Blob Storage, Event Grid, and Service Bus. Leveraged GitHub Copilot to accelerate implementation by generating high-quality code suggestions in real time. Utilized Copilot to reduce manual coding effort, enabling faster delivery of core features and enhancements. Applied Copilot for intelligent code completion, refactoring hints, and automated test generation. Improved development velocity and consistency by integrating Copilot into everyday coding routines across projects. Languages: PostgreSQL, Python, Yaml, MCP Integration Other tools: Generative AI, Azure OpenAI API, Restful API (FastAPI), Cursor AI, OTel, LangFuse, AKS, Docker Client: Walmart April 2022 December 2023 Role: Lead AI Engineer Leading the integration and enhancement of AI/ML capabilities within CORA Machine Vision, an advanced identity security AI platform. Focused on leveraging large language models (LLMs) and machine learning algorithms to enhance real-time identity threat detection, automate policy creation, and provide data-driven security insights. Collaborating with cross-functional teams to optimize AI workflows and ensure scalable, efficient deployment in cloud environments. Later Extended it to profiling the incidents using Agentic AI workflows orchestration. Responsibilities: Collaborated with the business team to finalize project charters and scopes. Spearheaded the integration of advanced AI/ML features into CORA Machine Vision, an identity security AI platform. Leveraged large language models (LLMs) and machine learning algorithms to enhance real-time identity threat detection and risk prediction. Automated policy generation workflows using AI, improving response times and reducing manual intervention in security protocols. Collaborated with data scientists, cloud engineers, and security experts to design scalable and efficient AI pipelines. Developed and optimized cloud-based deployment strategies to ensure high availability, performance, and security of AI models. Conducted regular evaluations of model performance, retraining strategies, and drift monitoring to maintain model accuracy in production. Created data-driven dashboards and reporting tools to deliver actionable security insights to stakeholders. Ensured alignment with enterprise-grade compliance and security standards during AI solution design and implementation. Championed the adoption of AI best practices, including ethical AI usage, explainability, and continuous learning mechanisms. Contributed to product strategy by identifying and prioritizing high-impact AI/ML use cases within the platform. Designed data models using conceptual, logical, and physical modelling principles to support AI- driven identity threat detection workflows. Used Bedrocks knowledgebase to store vector database. Utilized GitHub Copilot integration as part of the development. Integrated LangChain-based GenAI flows for automating security policy recommendations and real-time data synthesis. Leveraged Cursor AI to rapidly prototype features and ship functional code in compressed timelines. Utilized Cursor AI to auto-generate scaffolds, reduce boilerplate, and accelerate development cycles. Applied Cursor AI for context-aware refactoring, debugging, and multi-file code improvements. Improved delivery speed and code consistency by integrating Cursor AI into daily development workflow. Languages: SQL, PL/SQL, Python Other tools: Generative AI, GPT, Native LLMs setup, Restful API, GitHub Copilot for code development Client: TELUS Health August 2021 December 2022 Role: Lead & ML Engineer Developed an intelligent data pipeline that continuously collects and processes signals from grid and IoT devices, providing real-time visibility into network health. The solution enabled faster fault detection, predictive maintenance, and improved operational efficiency. Using Kafka-based event streaming, Python microservices, and cloud deployment, the system delivered reliable, low-latency insights, a scalable foundation adaptable to RFID and broader IoT applications. Responsibilities: Collaborated with the business team to finalize project charters and scopes. Designed and developed real-time data ingestion pipelines for monitoring smart meters, grid devices, and IoT sensors within power distribution networks. Engineered Python-based event processing systems to detect anomalies, track equipment health, and process telemetry data from distributed field devices. Built data streaming architectures using Kafka and RabbitMQ, ensuring reliable and low-latency communication between edge devices and central control systems. Integrated AI/ML and rule-based reasoning to predict equipment failures, energy theft, and irregular consumption patterns in utility networks. Collaborated with field and control teams to align IoT data with GIS, SCADA, and grid-asset management systems for actionable insights. Implemented data validation, de-duplication, and transformation workflows to clean and process raw telemetry data from noisy or intermittent sources. Deployed and managed containerized microservices on cloud and hybrid infrastructure to support distributed event processing and analytics. Introduced observability frameworks for monitoring pipeline health, latency, and message delivery across critical operational data systems. Worked on AI-driven automation of inspection and outage response workflows integrating Computer Vision and sensor data for equipment verification and field efficiency. Applied principles of real-time data fusion and event correlation, similar to RFID signal processing, enabling unified monitoring across diverse utility endpoints. Development accelerated using Blackbox coding assistance within VSC. Client: Enabil Solutions February 2018 Jun 2020 Role: Sr Data Engineer | ML Engineer This project delivers a scalable, machine learning-driven analytics system for minimizing non-technical losses such as energy theft and fraudulent billing. The solution processes both prepaid and postpaid customer data and integrates seamlessly with existing SAP systems to extract billing, consumption, and customer profile information. Responsibilities: Key outcomes include: Integrate with existing system, analyze customer usage and payment behaviors, detect fraudulent energy consumption and tampered meter readings, and optimize billing recovery strategies. Collaborated with the business team to finalize project charters and scopes. Integrated prepaid and postpaid customer, billing, and consumption data from SAP IS-U and external sources for unified analysis. Built scalable end-to-end machine learning pipelines using AWS services including S3, Glue, Lambda, and SageMaker. Performed data cleaning, transformation, and harmonization across SAP exports, recharge logs, and smart meter data. Engineered time-series and domain-specific features such as load factor deviation, usage-billing mismatch, and recharge irregularity. Conducted exploratory data analysis to identify suspicious behavior patterns and energy theft indicators. Developed supervised learning models including Logistic Regression, Decision Trees, Random Forest, and XGBoost for fraud detection. Validated models using confusion matrices, ROC-AUC, precision-recall curves, and cross-validation strategies. Applied hyperparameter tuning techniques such as GridSearchCV and handled class imbalance using methods like SMOTE. Built modular, reusable Jupyter notebooks for customer analysis, billing insights, fraud detection, and integrated reporting. Created visualizations to highlight fraud trends, customer clusters, and billing anomalies using matplotlib, seaborn, and Plotly. Automated retraining, fraud scoring, and alerting using AWS Lambda and integrated results into operational systems. Collaborated with business, billing, and field teams to translate domain knowledge into actionable model features and insights. Prepared APIs and data outputs for integration into SAP dashboards and enterprise fraud monitoring tools. Software: Scikit Learn, Pandas, Dask, AWS Services: S3, Lambda, Glue, SageMaker, CloudWatch Languages: SQL, Python, Bash/Shell Other tools: Scikit-learn, XGBoost, Pandas, NumPy, Matplotlib, Seaborn, Jupyter, VS Code, Restful API, Airflow. Client: Snapdeal February 2014 January 2018 Role: Software Engineer Responsibilities: Web Application Development: Developed and maintained web applications using PHP, MySQL, and CodeIgniter framework, ensuring high performance and scalability. Campaign Management: Worked on contract for 36 months, developing and managing internal targeting applications like ZAGAT, Coupon Tool, and Yesmail Client UI. AngularJS Application Development: Designed and implemented dynamic features for AngularJS-based applications to enhance user experience. 00000OOP & Scripting: Applied Object-Oriented Programming (OOP) principles and scripting languages such as JavaScript to build robust and scalable applications. Security & Encryption: Implemented encryption mechanisms for URLs and email verification processes, ensuring secure user authentication and data protection. Requirement Analysis & Planning: Conducted detailed project planning and requirement analysis to align development with business objectives and ensure smooth execution. Problem Solving & Process Improvement: Identified areas for process improvement, proposed solutions, and initiated corrective actions to enhance overall system efficiency. Communication & Documentation: Maintained clear and effective communication with stakeholders and documented technical concepts for seamless team collaboration. Client Collaboration: Worked closely with the team to understand project requirements, ensure adherence to specifications, and deliver innovative solutions. Continuous Learning: Kept abreast of emerging technologies and best practices in web development to consistently enhance skill sets. Software: SQL, MySQL, PHP, CodeIgniter, Linux, Microsoft PowerPoint Languages: SQL, PL/SQL, Shell script, PHP Other tools: SVN, Jira, Confluence, Oracle 11G/10G/9i Certification: Building intelligent agent workflows Building multi-agent systems Python for Data Science, AI & Development AI agent fundamentals with Azure AI Foundry Foundations of data science Education Bachelor of Technology in Computer Science & Engineering from SRM University -2014 Masters in Wilmington University IST - 2021 Keywords: continuous integration continuous deployment artificial intelligence machine learning user interface sthree database information technology procedural language Delaware