We are looking for an experienced LLMOps Engineer to join our team and lead the deployment, operation, optimization, and monitoring of Large Language Models (LLMs) and Generative AI applications in production environments.

The ideal candidate will have hands-on experience building scalable LLM applications, developing Retrieval-Augmented Generation (RAG) pipelines, evaluating model outputs, and optimizing AI systems for performance, reliability, and cost efficiency.

Key Responsibilities

· Deploy, serve, and manage Large Language Models (LLMs) in production environments.

· Design, develop, and maintain Retrieval-Augmented Generation (RAG) applications and pipelines.

· Build and optimize LLM inference and serving infrastructure.

· Implement LLM evaluation frameworks to measure accuracy, relevance, quality, and reliability of generated outputs.

· Monitor LLM applications and track performance, latency, token usage, and operational costs.

· Optimize prompt engineering, context management, and inference workflows.

· Work with vector databases and embedding models to build efficient semantic search solutions.

· Implement observability, logging, monitoring, and troubleshooting for LLM-powered applications.

· Optimize GPU utilization, model serving, and resource allocation.

· Implement scalable APIs and integrate LLMs into enterprise applications.

· Collaborate with AI Engineers, Data Scientists, Software Engineers, and DevOps teams.

· Ensure security, scalability, reliability, and governance of production GenAI solutions.

Requirements & Qualifications

· 5+ years of experience in AI/ML Engineering, MLOps, Software Engineering, or related fields.

· Strong programming skills in Python.

· Hands-on experience deploying and operating LLMs in production.

· Strong understanding of Transformer architectures and modern LLM technologies.

· Practical experience building RAG pipelines and LLM-powered applications.

· Experience with frameworks such as LangChain, LlamaIndex, or similar.

· Experience with vector databases such as Pinecone, Weaviate, Milvus, or Chroma.

· Knowledge of embedding models, semantic search, and reranking techniques.

· Experience with LLM evaluation tools and frameworks.

· Familiarity with model serving technologies such as vLLM, Hugging Face TGI, or NVIDIA Triton.

· Experience with Docker, Kubernetes, and CI/CD pipelines.

· Understanding of cloud platforms (AWS, Azure, or GCP).

· Knowledge of API development, monitoring, and production infrastructure.

· Ability to optimize LLM performance, scalability, and inference costs.

Good to Have

· Experience with fine-tuning techniques such as LoRA and QLoRA.

· Knowledge of quantization and model compression techniques.

· Experience with GPU infrastructure and distributed inference.

· Familiarity with LLM observability and tracing tools such as Langfuse, LangSmith, or Arize Phoenix.

· Experience implementing AI agents and multi-agent systems.

· Understanding of responsible AI, guardrails, and LLM security.