onsite
AI Architect - Fx31Labs Private Limited
Software Engineer
Senior AI Engineer specializing in designing and deploying enterprise‑grade, LLM‑powered agentic solutions using frameworks like LangChain, LangGraph, and Semantic Kernel, with expertise in RAG and advanced prompt engineering.
About the role
Key Responsibilities
- Architect and implement AI agent workflows using LangChain, LangGraph, or Semantic Kernel to solve complex business problems.
- Design Retrieval‑Augmented Generation (RAG) pipelines and integrate them with large language models for accurate, context‑aware outputs.
- Develop prompt engineering strategies, fine‑tune models, and create reusable prompt libraries.
- Collaborate with cross‑functional teams to translate requirements into scalable AI solutions and ensure seamless deployment in cloud environments.
- Monitor performance, conduct A/B testing, and continuously optimize models for latency, cost, and accuracy.
Requirements
- 6–10 years of hands‑on experience building AI agents or multi‑agent systems with LLMs.
- Proficiency in at least one orchestration framework: LangChain, LangGraph, or Semantic Kernel.
- Strong background in Retrieval‑Augmented Generation, prompt engineering, and model fine‑tuning.
- Experience deploying AI services on cloud platforms (e.g., Azure, AWS) and managing production‑grade pipelines.
- Excellent problem‑solving skills and ability to communicate complex AI concepts to technical and non‑technical stakeholders.