FullStack Engineer AI Expertise

Overview

We are seeking a Full Stack Engineer with strong AI knowledge to work onsite at our client location
, contributing to the development of AI‑enabled applications and cloud‑native platforms. The role involves full‑stack development along with hands‑on integration of Generative AI/LLM capabilities, agentic frameworks, and the latest AI tool chains.

• Full Stack Engineering
  • Develop and maintain full‑stack applications using Python or Go.
  • Build backend microservices, APIs (REST/gRPC), and cloud‑native services.
  • Contribute to frontend development using modern frameworks (React, Angular, Vue).
  • Deploy applications on AWS, Azure, or GCP.
  • Work onsite at client premises as part of daily collaboration.
• AI Engineering
  • Integrate business applications with LLMs (OpenAI, Azure OpenAI, Anthropic, Vertex AI).
  • Develop AI‑driven workflows using:
  • MCP (Model Context Protocol)
  • Agentic AI frameworks (Crew AI, Auto Gen, Agent Ops)
  • Lang Chain
  • Work with embeddings, vector search, and retrieval pipelines.
  • Collaborate with AI/ML teams to product ionize models.

• U.S. Citizen (mandatory due to client requirements).
• 5–7 years of full‑stack development experience.
• Strong skills in Python and/or Go.
• Hands‑on experience with cloud environments (AWS/Azure/GCP).
• Experience integrating with Generative AI / LLM APIs.
• Knowledge of MCP, agentic frameworks, and Lang Chain.
• Proficiency in relational/No
  
  SQL databases.
• Ability to work onsite at client’s workplace.

• Experience with vector databases
• Familiarity with serverless architectures.
• Background working in regulated or secure environments (nice to have).