LLMOps Developers

Job Summary

Job Title: LLMOps Engineer

Locations: Hyderabad, India | Hybrid

Responsibilities

• Maintain automated CI/CD pipelines dedicated to model prompt deployments, vector index updates, and agent graph configurations.
• Monitor live production model endpoints for latency spikes, token utilization, response drift, and output accuracy degradation.
• Administer, re-index, and optimize vector databases (Milvus, Qdrant, Pinecone) to maintain peak search precision over time.
• Build observability dashboards to track API token costs, rate limits, and model utilization across internal business groups.
• Configure tracing platforms (LangSmith, Phoenix, Arize) to capture step-by-step agent decisions and tool execution history.
• Support regular regression test suites prior to updating underlying foundation models or system configurations.

Requirements

• 4 - 7 years in software engineering, DevOps, or ML platform maintenance, with 2+ years dedicated to LLM deployment operations.
• Hands-on experience with LLM observability, tracing, and evaluation tools (LangSmith, LangFuse, Arize, TruLens).
• Working knowledge of vector database management, indexing parameters (HNSW, IVFFlat), and payload filtering optimization.
• Strong Python programming skills, with direct experience handling REST APIs, FastAPI, and containerized deployments.
• Clear understanding of version control strategies for prompt engineering and vector database migrations.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.