AI Architecture & Leadership:

- Design and implement multi-agent AI systems for enterprise workflows.

- Develop and optimize RAG pipelines for knowledge retrieval and contextual reasoning.

- Integrate MCP for tool and API interoperability across AI agents.

- Apply context engineering to improve agent reasoning and reliability.

Model Development:

- Fine-tune LLMs and transformer-based models for domain-specific tasks and enterprise use cases.

- Evaluate trade-offs between fine-tuning, prompt engineering, and RAG for optimal performance.

- Collaborate with data scientists to design custom embeddings and model adaptations.

Data & Knowledge Engineering:

- Build and manage data pipelines for ingestion, transformation, and retrieval.

- Design and maintain knowledge graphs using Neo4J or similar graph databases to support semantic search and contextual reasoning.

- Integrate knowledge graphs with RAG pipelines for enhanced retrieval.

Development & Deployment:

- Lead development using Python (LangChain, HuggingFace, LangGraph, Google ADK, Microsoft Agent Framework etc.).

- Collaborate with front-end teams using ReactJS (nice to have) for AI dashboards and agent interaction UIs.

- Ensure scalability, observability, and reliability of AI systems using AIOps practices.

Leadership & Collaboration:

- Mentor and guide engineering teams in AI best practices.

- Collaborate with product managers, data scientists, and stakeholders to align AI solutions with business goals.

- Drive innovation by evaluating emerging AI technologies and frameworks.