LLM / GenAI Engineer

About The Role The role is for someone who moves beyond basic prompt engineering and understands how to build reliable, scalable GenAI applications, including advanced RAG systems, multi-agent workflows, and fine-tuning pipelines. The team works at the intersection of applied research and systems engineering, tackling challenges in latency, hallucination reduction, and context optimization. Key Responsibilities • Design and deploy production-grade RAG architectures with advanced chunking, re-ranking, and hybrid search capabilities • Integrate and manage vector databases such as Pinecone, Qdrant, or pgvector to ensure low-latency semantic retrieval at scale • Build automated evaluation and guardrail frameworks using LLM-as-a-judge patterns and benchmark datasets • Fine-tune open-source foundational models using parameter-efficient methods like LoRA and QLoRA on secure datasets • Optimize inference latency and token usage through quantization, caching, and model distillation techniques • Collaborate with backend engineers to integrate LLM services into existing microservices and RESTful APIs What We Are Looking For • 3-6 years of professional software engineering experience, with a minimum of 2 years dedicated to building LLM or GenAI applications in production • Strong proficiency in Python and hands-on experience with orchestration frameworks such as LangChain or LlamaIndex • Deep understanding of embedding models, vector search dynamics, and context window management • Experience with model hosting, inference optimization, and cloud platforms like AWS, GCP, or Azure • BS or MS in Computer Science, Artificial Intelligence, or a related technical field • Bonus: Contributions to open-source AI projects, experience with multi-agent frameworks like AutoGen, or published research in NLP/GenAI