Software Engineer, AI/ML GenAI - Onsite - SF

About the role One of our start-up clients is looking for a Software Engineer, AI/ML GenAI with 5-8 years of experience to join our growing team. The ideal candidate is a great software engineer first and foremost, with a strong background in Python, who has transitioned into working with modern LLMs over the last few years. You will be instrumental in taking our AI features from prototype to production, building resilient, scalable systems that directly impact our nonprofit clients. What will you be doing? Design, build, and ship agentic LLM systems and other AI features into production, owning the full lifecycle from prototyping to deployment and maintenance. Own and improve our Retrieval-Augmented Generation (RAG) pipelines end-to-end, including ingestion, chunking, embedding, and retrieval strategies. Manage embeddings and vector stores at scale, ensuring the health and performance of our indices. Develop and implement robust evaluation and observability frameworks to ensure our AI is grounded, safe, and cost-effective. Collaborate closely with product, design, and other engineers to build customer-facing features that help nonprofits secure funding more efficiently. Seniority 5 -​ 8 years of experience in SWE at an LLM-​centric company Work experience Built and shipped production-​level LLM/RAG systems,​ including embeddings and vector databases (not just prototypes).​ Experience at a startup (Series A-​C) is strongly preferred.​ Worked at a company where ML/AI is core to the product.​ Hard skills Experience with Python is essential for our LLM stack.​ Built agentic LLM systems using tools like LangChain/LlamaIndex. Salary $175K - $220K Equity Competitive equity. On-site or Remote work policy 1 day in-office in San Francisco Visa sponsorship not available Full-time position