GenAI/LLM engineering

Key Responsibilities: Develop autonomous AI agents capable of planning, reasoning, and task execution. Build and orchestrate multi-agent workflows using LangGraph or similar frameworks. Integrate LLMs such as Claude/GPT through AWS Bedrock and other enterprise AI services. Develop MCP-based tools and integrations for APIs, document processing, search, analytics, and reporting. Build scalable Python services, APIs, ETL pipelines, and data integrations. Implement RAG, vector search, and knowledge retrieval solutions. Ensure observability, monitoring, auditability, security, and AI governance controls. Develop Human-in-the-Loop (HITL) workflows and validation mechanisms. Mandatory Skills Python, FastAPI, REST APIs LangGraph and Agentic AI frameworks (Claude Agent SDK, CrewAI, AutoGen, Semantic Kernel, etc.) Multi-Agent Systems and Workflow Orchestration Claude/GPT Models and AWS Bedrock Prompt Engineering and Context Engineering PostgreSQL, pgVector, Vector Databases, RAG AWS, Docker, ECS/EKS, CI/CD AI Governance, Monitoring, and Audit Controls

Preferred Skills: MCP Server Development Knowledge Graphs Multi-modal Document Processing Agent Evaluation & Monitoring Frameworks Sustainability / Climate Data Platforms AWS Solution Architecture Certification Experience 3 years of GenAI/LLM engineering experience. Proven experience building production-grade AI agents and cloud-native platforms. Strong understanding of AI governance, risk controls, and enterprise deployment practices.