Key Responsibilities:
Agentic AI Architecture & Development
- Design and build production-grade multi-agent systems using LangGraph, LangChain, CrewAI, and AutoGen
- Architect agent orchestration patterns including planning, tool usage, memory, reflection, and state management
- Develop RAG pipelines including document processing, chunking, embeddings, and vector database integration
- Build evaluation, testing, and observability frameworks for AI agents in production
- Design natural language-to-data query systems integrating with platforms like Databricks Genie
LLM Integration & Optimization
- Integrate LLM/SLM services (OpenAI, Azure OpenAI, Anthropic, open-source models)
- Apply prompt engineering techniques such as few-shot learning and chain-of-thought reasoning
- Implement safety guardrails, filtering, and responsible AI controls
- Benchmark models based on cost, latency, accuracy, and domain performance
Platform & Backend Engineering
- Build scalable Python backend services using FastAPI
- Implement caching, rate limiting, persistent memory, and agent state management
- Develop event-driven microservices and real-time streaming systems
- Integrate AI agents with enterprise systems and external APIs
- Use distributed task processing (Celery) and autoscaling (KEDA)
Innovation & Technical Leadership
- Evaluate emerging Agentic AI frameworks and technologies
- Lead proof-of-concept development and production deployment of AI solutions
- Mentor engineers on AI architecture, prompt engineering, and agent design
- Contribute to architecture documentation and technical design standards
- Promote AI-powered development tools across engineering teams
