LLM / GenAI Engineer

About The Role The role focuses on building and optimizing production-grade Generative AI systems, moving beyond basic API wrappers to design robust Retrieval-Augmented Generation (RAG) pipelines, agentic workflows, and fine-tuning pipelines. The engineer will work closely with data platform teams and product engineers to integrate large language models into enterprise-scale features where throughput, latency, cost, and accuracy are critical constraints. Key Responsibilities Design and optimize RAG pipelines utilizing advanced chunking strategies, reranking models, and hybrid search methods. Build and maintain high-performance vector database integrations using tools like Qdrant, Pinecone, or pgvector at scale. Implement systematic LLM evaluation and monitoring frameworks to detect hallucinations, measure response quality, and track latency. Fine-tune open-source models (such as Llama, Mistral) using parameter-efficient methods like LoRA and QLoRA for domain-specific tasks. Develop and deploy robust orchestration layers and agentic workflows using LangChain, LangGraph, or custom lightweight frameworks. Collaborate with MLOps to containerize, deploy, and monitor LLM inference endpoints in cloud environments using vLLM or Triton Inference Server. 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 software engineering fundamentals in Python, including async programming, API development (FastAPI), and writing comprehensive unit and integration tests. Hands-on experience with vector databases and semantic search optimization. Familiarity with model optimization techniques such as quantization, caching strategies, and structured output generation (e.g., Outlines, Instructor). Bachelor's degree in Computer Science, engineering, or a related quantitative field, or equivalent practical experience. Bonus: Experience with direct fine-tuning datasets preparation, hands-on Kubernetes usage, or contributions to open-source GenAI frameworks. Show more Show less