LLMOps Engineer (Bengaluru)

LLMOps Engineer (Bengaluru)

17 Nov
|
Aventra.AI
|
Bengaluru

17 Nov

Aventra.AI

Bengaluru

Location:
Bengaluru

Experience:
8+ Years Relevant

Experience:
Minimum 4+ Years in AI Work Mode: To be confirmed Job Overview We are looking for an experienced LLMOps Engineer with strong expertise in Generative AI, Large Language Models (LLMs), RAG pipelines and production AI infrastructure. The ideal candidate should have hands-on experience building, deploying, monitoring, evaluating and optimizing enterprise-grade LLM applications. The candidate will be responsible for establishing scalable LLMOps practices, managing model lifecycle operations and ensuring reliability, performance, security and cost efficiency of AI-powered applications.

Key Responsibilities
• Design, develop and implement end-to-end LLMOps pipelines for enterprise GenAI applications.
• Deploy, manage and monitor LLMs across AWS, Azure or GCP environments.
• Build and optimize RAG pipelines, including document ingestion, chunking, embeddings, retrieval and reranking.
• Implement model evaluation frameworks to measure accuracy, relevance, faithfulness, hallucination and response quality.
• Develop automated CI/CD pipelines for LLM applications, prompts, models and AI workflows.
• Implement LLM monitoring, tracing, logging and observability.
• Optimize inference latency, token consumption, throughput and model deployment costs.
• Implement model versioning, prompt versioning and evaluation benchmarks.
• Work with vector databases such as Pinecone, FAISS, ChromaDB, Weaviate or Milvus.
• Build scalable AI services using Python, FastAPI and microservices architecture.
• Implement model serving, API gateways, caching and load balancing.
• Collaborate with AI Engineers,



ML Engineers, Data Engineers and DevOps teams.
• Establish production monitoring, incident management and continuous improvement processes. Mandatory Technical Skills
• Robust Python programming and software engineering experience.
• Minimum 4+ years of hands-on experience in AI, Generative AI, LLMs and RAG.
• Strong understanding of LLMOps and MLOps practices.
• Experience with OpenAI, Azure OpenAI, Claude, Gemini or open-source LLMs.
• Hands-on experience with RAG architecture and implementation.
• Experience with LangChain, LangGraph or similar frameworks.
• Knowledge of embeddings, semantic search and vector databases.
• Experience with LLM evaluation frameworks such as RAGAS, DeepEval, TruLens or LangSmith.
• Experience with model monitoring, tracing and observability.
• Strong experience with Docker, Kubernetes and CI/CD.
• Cloud experience with AWS, Azure or GCP.
• Experience deploying and managing production-grade AI applications. Good to Have
• Experience with vLLM, Hugging Face, Ollama or NVIDIA Triton.
• Knowledge of model quantization and inference optimization.
• Experience with MLflow, Kubeflow or KServe.
• Knowledge of LLM-as-a-Judge and automated AI evaluation.
• Experience with MCP and Agentic AI systems.
• Knowledge of GPU infrastructure and distributed inference. Candidate Expectations
• Strong production-level LLMOps implementation experience.
• Ability to design scalable and reliable AI infrastructure.
• Strong troubleshooting, optimization and performance engineering skills.
• Experience managing AI applications throughout their production lifecycle.

📌 LLMOps Engineer (Bengaluru)
🏢 Aventra.AI
📍 Bengaluru

Reply to this offer

Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.

Subscribe to this job alert:

Get the latest job offers by email for: llmops engineer (bengaluru) / bengaluru

Subscribe to this job alert:

Get the latest job offers by email for: llmops engineer (bengaluru) / bengaluru