- Design and develop scalable Agentic AI applications using multi-agent orchestration, ReAct frameworks, and tool/function calling.

- Build advanced retrieval systems using GraphRAG, multi-hop retrieval, vector databases, and long-term memory architectures.

- Develop secure AI solutions by implementing AI guardrails, data privacy, compliance controls, and secure AI gateways.

- Create evaluation and monitoring frameworks using LLM-as-a-Judge, tracing, telemetry, and offline evaluation datasets.

- Optimize AI workflows for latency, scalability, token usage, and infrastructure costs through model routing and caching strategies.

- Integrate AI solutions with enterprise databases, APIs, and business applications while ensuring high availability.

- Mentor engineering teams on Agentic AI design patterns and best practices.

- Identify innovative AI use cases that deliver measurable business value and drive enterprise AI adoption.

Required Skills :

- 8+ years of software engineering experience with strong expertise in Generative AI and LLM technologies.

- Hands-on experience with Agentic AI frameworks, multi-agent systems, and ReAct architectures.

- Strong knowledge of RAG, GraphRAG, vector databases, embeddings, and retrieval optimization.

- Experience with enterprise AI security, governance, compliance, and AI guardrails.

- Expertise in AI observability, evaluation frameworks, and LLM performance monitoring.

- Proficiency in Python, REST APIs, cloud platforms (AWS/Azure/GCP), and microservices architecture.

- Experience integrating AI solutions with enterprise systems, databases, and APIs.

- Excellent problem-solving, communication, and stakeholder management skills.