I am a Senior AI/ML Engineer specializing in LLM systems, agentic AI, and production machine learning.

My work focuses on taking models from research to reliable, monitored, and scalable production systems that deliver real business impact.

• LLM Engineering: RAG, tool-using agents, prompt systems, evaluation, safety
• Agentic AI: LangGraph, AutoGen, CrewAI, multi-agent orchestration
• MLOps: MLflow, model serving, CI/CD for ML, monitoring and drift detection
• Data & ML Pipelines: feature engineering, training workflows, inference optimization
• Cloud Infrastructure: AWS, Kubernetes, Docker, Terraform

Stack: OpenAI, LangChain, Python, PostgreSQL, Docker, Kubernetes

• Agent-based orchestration with tool calling and memory
• RAG pipelines with vector databases and evaluation gates
• Monitoring, retries, and hallucination mitigation

Stack: PyTorch, Ray, MLflow, AWS, Terraform

• Cost-aware model scheduling and autoscaling
• Model lifecycle management and experiment tracking
• Zero-downtime deployments for inference services

• Agentic AI and autonomous LLM systems
• LLM evaluation, guardrails, and observability
• Scalable MLOps and governance
• Responsible and secure AI deployment