Sree Sathvik Chilamkurthy

GenAI Engineer with 6+ years of experience building intelligent AI systems, deploying scalable machine learning platforms, and delivering cloud-native solutions across enterprise environments. Strong expertise in LLM-powered automation, advanced machine learning, Python, Kubernetes, Terraform, CI/CD, and production-grade AI/ML systems. Skilled in RAG, semantic search, hybrid search, predictive modeling, and data transformation using LangChain, LangGraph, OpenAI APIs, and modern AI orchestration frameworks. Developed intelligent agents with tool calling, dynamic workflow orchestration, conditional routing, and API integration for multi-step automation. Implemented asynchronous Python workflows, stateful conversational systems, memory-enabled AI assistants, and multi-agent collaboration frameworks for scalable enterprise AI applications. Built human-in-the-loop validation, AI guardrails, response governance, prompt lifecycle management, and traceable AI workflows to improve reliability, reproducibility, explainability, and auditability. Proficient in LLM orchestration, including prompt chaining, agent state graphs, structured outputs, and reflection-based feedback loops. Delivered scalable pipelines using Python, FastAPI, Docker, Databricks, and Delta Lake across Azure, AWS, and GCP. Expert in vector databases like Pinecone, FAISS, and Weaviate for optimized retrieval, knowledge management, and AI search systems. Built ML solutions for risk scoring, telematics underwriting, clustering, regression, forecasting, and sentiment analysis using XGBoost, PySpark, Scikit-Learn, and Azure ML. Applied MLOps, model monitoring, data quality validation, and governance using Great Expectations and Azure Purview. Fine-tuned open-weight LLMs (e.g., Mistral, LLaMA) with LoRA, PEFT, and implemented model routing and optimization strategies for latency-accuracy tradeoffs.