AI Software Engineer (Python, LLM, RAG)

AI Software Engineer (Python, LLM, RAG)Prestigious Global Financial Organization | New York, NY (Onsite 3-4 days/week)Most AI engineering jobs are demos and prototypes. This one ships. Our client, a world-class organization whose work spans professional information services and global philanthropy, is building AI into the tools thousands of professionals rely on every day, and they need an engineer who can take LLM-powered features from idea to production.The RoleYou'll design, build, and ship AI-powered applications end to end: working with large language models, building the pipelines and services around them, and partnering directly with business teams to turn real problems into working products. This is a hands-on software engineering role first — AI is the toolkit, shipping is the job.You'll get rare range here: use cases across legal and policy intelligence, research, and mission-driven programs, with the resources of a world-class technology organization behind you.What You'll NeedStrong software engineering fundamentals — Python, APIs, production servicesHands-on experience building with LLMs: RAG pipelines, prompt engineering, embeddings, agentsExperience taking AI features to production, not just proof of conceptComfort working directly with non-technical stakeholders to shape use casesNYC-based, onsite 3-4 days a weekBonus PointsCloud AI platforms (Azure OpenAI, AWS Bedrock, Vertex AI)Vector databases, orchestration frameworks (LangChain, LlamaIndex, or similar)Data engineering or MLOps backgroundWhy This RoleAI roles this hands-on, with this much organizational backing and this little bureaucracy, are rare. You'll see your work used by real professionals within weeks, not quarters, and you'll be early on a team that's defining how one of the world's most respected organizations uses AI.