*Nice software* no Hyderabad Candidates

*We will need the UAN and BGV.*

*Job Description: LLM Engineer*

*Experience: 4+ years*

Budget: 80K

*About the Role*

We're looking for an LLM Engineer to build, deploy, and scale production-grade Generative AI systems : spanning agentic workflows, RAG pipelines, evaluation, and backend infrastructure. This role is deployment- and infrastructure-heavy, focused on serving LLM and agentic applications reliably at scale while keeping quality, cost, and latency in check.

Key Responsibilities

Agentic Systems

- Build agent workflows using frameworks such as LangGraph, CrewAI, AutoGen, or the OpenAI Agents SDK
- Implement function calling and tool use so agents can reliably invoke APIs, databases, and internal services
- Use MCP (Model Context Protocol)



or similar standards to connect agents to external tools and data sources in a consistent, maintainable way
- Add guardrails and fallback handling to keep multi-step agent behavior predictable and secure in production

Retrieval-Augmented Generation (RAG)

- Build and tune RAG pipelines, including chunking strategy, embedding model selection, and re-ranking
- Deploy, scale, and evaluate vector databases such as Pinecone, Qdrant, FAISS, pgvector, ChromaDB, Milvus, or Azure AI Search for high-volume retrieval
- Diagnose hallucinations and weak answers by tracing them back to retrieval issues rather than treating every problem as a prompting issue

Pay: ₹80,000.00 - ₹100,000.00 per month

Work Location: Remote

📌 LLM Engineer (India)
🏢 FuGenTex Solutions
📍 India