Key Responsibilities:
- Design and architect scalable agentic AI systems.
- Build production-ready GenAI applications with focus on reliability and performance.
- Develop and optimize RAG/GraphRAG pipelines.
- Lead technical implementation and establish best practices.
- Mentor engineering teams on AI/ML architecture and implementation.
Key Skills Required:
- Hands-on experience shipping production-ready generative AI applications at scale serving real users.
- Strong understanding of LLM/ Agent internals: context window management, MCP Servers, tool calling loops, prompt and context engineering, architecture trade-offs etc.
- Proven experience with LangGraph, CrewAI, Semantic Kernel or similar agentic frameworks to design complex multi-agent architectures and low code/ no code tools like Agent Kit, Copilot Studio.
- Experience building sophisticated RAG and GraphRAG pipelines with vector databases and knowledge graph-based retrieval.
- Practical experience leveraging coding agents (Claude Code, Codex) for spec-based rapid development with tools like spec-kit.
- Production cloud experience deploying and scaling AI applications on AWS, GCP, or Azure.
- Proven track record mentoring junior and senior developers with strong technical communication skills.
Technical Stack: Python, LangGraph/CrewAI, OpenAI/Claude/Gemini APIs, Vector DBs, Cloud platforms - (AWS/GCP/Azure), Graph Databases.
Required Qualifications and Experience:
8-12 years software engineering experience
2+ years hands-on experience with LLMs and generative AI
Bachelor's/Master's in Computer Science, AI/ML, or equivalent experience
