Educational Qualification* B.E / B.Tech / BCA / MCA or equivalent in Computer Science / IT

Experience Range:8-12 years of overall IT experience

Tagline/Tech Stack Snapshot - AI Lead (10+ Years) Python, Generative AI, Agentic AI, Machine Learning, Deep Learning, FastAPI, AWS Bedrock, LangChain/Strands, Vector Databases, OpenSearch, REST APIs

Role Summary - We are seeking a highly experienced AI Lead (10+ years) to join the Nucleus AI project and lead the design, development, and implementation of enterprise-grade AI solutions. The candidate will be responsible for building scalable GenAI and Agentic AI applications using Python, FastAPI, AWS AI services, Retrieval-Augmented Generation (RAG), and modern AI orchestration frameworks. The role requires strong hands-on development skills along with the ability to design AI architectures, mentor team members, and collaborate with cross-functional stakeholders to deliver secure, scalable, and production-ready AI capabilities.

Primary (Must have skills)*

• 10+ years of software development experience with Python
• 5-7 years experience in Machine Learning and Deep Learning concepts
• 3 years of experience in Generative AI and Large Language Models (LLMs)
• 3 years of experiencein building Agentic AI solutions using frameworks such as LangGraph, CrewAI, AutoGen
• 5 years of experience in FastAPI and REST API development
• 3 years of experience implementing Retrieval-Augmented Generation (RAG) solutions
• 3 years of experience with Vector Databases (OpenSearch, Pinecone, FAISS, ChromaDB, etc.)
• 5 years of Experience with AWS services including Bedrock, Lambda, S3, IAM, Step Functions, API Gateway, CloudWatch
• 3 years of experience integrating foundation models (Claude, Llama, Titan, GPT, etc.)
• 7+ years of experience in debugging, optimization, and performance tuning skills




• 5-7 years of experience with Git, CI/CD pipelines, and Agile/Scrum delivery

Job Description of Role* (RNR) -

• Design, develop, and maintain scalable AI services using Python and FastAPI.
• Build and optimize Generative AI and Agentic AI workflows using enterprise AI frameworks.
• Develop Retrieval-Augmented Generation (RAG) pipelines for intelligent document search and contextual AI responses.
• Integrate LLMs hosted on AWS Bedrock and implement prompt engineering strategies.
• Develop AI services for semantic search, document summarization, comparison, and citation generation.
• Design and optimize vector search solutions using OpenSearch or other vector databases.
• Implement secure, scalable REST APIs and integrate them with frontend applications.
• Collaborate with architects, UI/UX, QA, DevOps, and business stakeholders throughout the delivery lifecycle.
• Ensure code quality through peer reviews, unit testing, and adherence to best practices.
• Troubleshoot production issues, optimize AI model performance, and contribute to continuous improvements.
• Mentor junior developers and provide technical guidance on AI solution design and implementation.

Secondary Skills (Good to have) Solid expertise in:
• Knowledge of MCP (Model Context Protocol)
• Experience with LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or Strands Framework
• Experience with Neo4j or Knowledge Graphs
• Familiarity with Prompt Engineering and AI Guardrails
• Experience with Docker, Kubernetes, and Terraform
• Exposure to Azure OpenAI or Google Vertex AI
• Experience with healthcare or life sciences domain
• Experience with observability tools and AI evaluation frameworks (RAGAS, DeepEval, TruLens, LangSmith)
• Understanding of secure AI development, responsible AI, and governance principles.

📌 TL/Sr TL - GenAI (Hyderabad)
🏢 WinWire
📍 Hyderabad