LLM / GenAI Engineer

About The Role The role focuses on building, optimizing, and deploying production‑grade Generative AI applications and Large Language Model (LLM) workflows. The engineering team is moving past simple prompting to construct robust Retrieval‑Augmented Generation (RAG) systems, agentic workflows, and customized fine‑tuning pipelines that operate reliably at scale. The engineer will collaborate closely with backend engineers, data platform teams, and product managers to integrate intelligent capabilities into core software systems. This role demands a strong software engineering foundation combined with deep practical knowledge of LLM APIs, vector databases, and evaluation frameworks. Key Responsibilities Design, implement, and scale production RAG pipelines using advanced retrieval strategies, query rewriting, and reranking techniques Build and maintain integrations with vector databases such as Pinecone, Qdrant, or pgvector, optimizing for query latency and retrieval recall Develop systematic LLM evaluation and observability frameworks to monitor model behavior, hallucination rates, and semantic drift in production Implement parameter‑efficient fine‑tuning (PEFT, LoRA, QLoRA) and instruction‑tuning pipelines to specialize open‑source models for domain‑specific tasks Optimize model serving infrastructure for high‑throughput and low‑latency inference, utilizing tools like vLLM, TensorRT‑LLM, or Triton Inference Server Deploy microservices and orchestrate workflows using containerized environments on cloud platforms like AWS or GCP What We Are Looking For 3-6 years of software engineering experience, with at least 1.5 years dedicated to building and deploying LLM‑based applications in production Strong proficiency in Python, including experience with asynchronous programming, FastAPI, and robust testing frameworks Hands‑on experience with LLM orchestration and development frameworks such as LangChain, LlamaIndex, or DSPy Solid understanding of vector search mechanics, semantic embeddings, and database optimization techniques Familiarity with cloud‑native infrastructure, including Docker, Kubernetes, and managed ML platforms like AWS SageMaker or run.ai Bonus: Experience with open‑source model optimization, custom model evaluations (e.g., Ragas, TruLens), or contributing to popular generative AI libraries #J-18808-Ljbffr Evlo AI