Senior Agentic AI Full Stack Developer

Full Stack Engineer proficient in Python, with proven ability to build production-grade multi-agent AI systems , API s and UI

Key Responsibilities

• Build and deploy agentic AI systems multi-agent pipelines, LLM orchestration, tool-use, and RAG workflows
• Design and develop production grade full stack applications and API's with Python and Golang backends
• Integrate LLM APIs (OpenAI, Anthropic, Gemini) and open-source models into production applications
• Build responsive, production-grade UIs that surface agentic AI capabilities to end users
• Build data management pipelines for agents data ingestion, cleaning, chunking, and structured injection into vector stores and memory layers
• Ensure data quality and consistency across agent context windows, retrieval pipelines, and tool inputs
• Develop responsive frontend interfaces to surface AI capabilities to end users
• Lead client-facing technical discussions requirements gathering, architecture walkthroughs, and delivery reviews
• Take end-to-end technical ownership of engagements from PoC through production handoff
• Collaborate with AI/ML and DevOps teams on inference stack integration and system observability

Requirements s Skills

Must-Have

• 5+ years of full stack engineering experience
• Proficiency in Python and Golang for backend development
• Hands-on experience building agentic AI systems LangChain, LangGraph, CrewAI, AutoGen, or equivalent
• Strong UI/frontend skills with framework like React , with ability to design clean, functional interfaces
• Familiarity with LLM APIs, cotext engineering, and RAG pipeline design
• Experience with REST/gRPC API design and microservices architecture
• Frontend development skills (React or equivalent)
• Experience with vector databases (Pinecone, Weaviate, pgvector)
• Exposure to observability tooling for AI systems (LangSmith, LangWatch, Helicone)
• Strong communication skills able to lead client interactions and own technical narratives

Good to Have

• Containerization and cloud deployment (Docker, Kubernetes, AWS/Google Cloud Platform)
• Familiarity with streaming inference and low-latency serving patterns