Description

You will design and implement Agentic AI systems and lead the end-to-end architecture of Generative AI applications.

This role is on-site.

Responsibilities

• Design multi-agent and goal-oriented systems using frameworks like AutoGen, LangGraph, and CrewAI.
• Develop reusable architectural patterns, best practices, and governance frameworks for GenAI development.
• Ensure scalability, performance, security, cost-effectiveness, and maintainability of GenAI applications.
• Implement robust LLMOps for continuous integration, deployment, monitoring, logging, and troubleshooting.
• Collaborate with Data Scientists and Product Owners to translate business problems into AI-powered solutions.

Required Skills

• 15+ years in software/solution architecture with proven experience as a Data Scientist or ML Engineer.
• Expertise in Agentic AI frameworks (AutoGen, LangGraph, CrewAI) and LangChain.
• Proficiency in Prompt Engineering, few-shot prompting, chain-of-thought reasoning, and prompt templates.
• Experience designing and deploying RAG pipelines, Vector databases, MCP Servers, and A2A.
• Cloud-native AI platform experience (AWS Bedrock, Azure OpenAI, Vertex AI).
• Proficiency in Python (preferred), Java, or Node.js for integration.
• Experience with Microservice architecture, Spring Boot REST APIs, API Security, and Versioning.
• Containerization technologies (Docker, Kubernetes) and CI/CD pipelines.
• Experience with AI Code Assist tools (Copilot, Windsurf, Cursor).

Preferred Skills

• Programming proficiency in Java or Node.js.
• Experience with Spring Cloud and PCF.

Key Skills

Education

Any Graduate