LLM / GenAI Engineer

About the role

The role focuses on building production-grade generative AI systems, moving beyond simple prompting into robust architectures like advanced RAG, agentic workflows, and fine-tuning pipelines. The team works at the intersection of applied research and scalable backend engineering to deliver reliable, low-latency, and context-aware AI applications for enterprise users.

Responsibilities

• Design, build, and optimize production-grade RAG pipelines utilizing advanced chunking, hybrid search, and re-ranking strategies
• Integrate and manage vector databases such as Pinecone, Weaviate, or pgvector for high-performance semantic retrieval
• Execute parameter-efficient fine-tuning (LoRA, QLoRA) on open-source foundation models using PyTorch and Hugging Face
• Develop automated LLM evaluation frameworks using LLM-as-a-judge patterns, deterministic test suites, and hallucination metrics
• Collaborate with backend engineers to deploy scalable inference endpoints with vLLM, Triton, or managed cloud APIs
• Monitor deployed LLM applications for latency, token costs, drift, and quality degradation using observability tools like LangSmith or Arize

Requirements

• 3-6 years of software engineering or machine learning experience, with a minimum of 2 years dedicated to building and deploying LLM applications in production
• Expert proficiency in Python and deep familiarity with LLM orchestration frameworks such as LangChain or LlamaIndex
• Hands-on experience with vector embeddings, semantic search infrastructure, and prompt engineering techniques
• Solid understanding of cloud infrastructure (AWS, GCP, or Azure) and containerization tools like Docker and Kubernetes
• Bachelor's degree in Computer Science, Artificial Intelligence, or equivalent practical experience

Skills

• Contributions to open-source AI projects
• Experience with multi-agent frameworks
• Published paper in NLP/ML