Applied AI Engineer - Onsite - SF / NYC

NOTE : ONLY Candidates with Bachelors in top CS program in US with 3+ experience need to apply. Masters degree in any field will not be consideredAbout the jobOne of our start-up clients is hiring a full-time Applied AI Engineer to own the prompts, agents, evals, and pipelines behind user-facing features that ship to users. You'll take product requirements and turn them into working prompts, agents, and pipelines. You'll evaluate them rigorously, iterate until they're production-ready, and keep improving them once they ship. This role sits at the intersection of product and platform: you decide what the AI should do, prove it works, and get it in front of users. Because we're an early-stage company moving fast, we're looking for someone who can work quickly through ambiguous AI problems, measure output quality, and ship only when the system is reliable enough for production. This is an in-person role, 5 days a week in our office. The ability to tell the difference between "looks good in the demo" and "works in production" is essential. Key ResponsibilitiesBuild new AI features end to end, from prototype to production.Improve AI output quality through prompt engineering, model selection, retrieval, and evaluation.Design and run evals that measure real output quality, not just first impressions.Iterate fast on prompts, agent designs, and orchestration patterns.Partner with the Product Engineer to translate requirements into AI features that actually work.Partner with the AI Platform team to land features on solid infrastructure.Evaluate new models, tools, and techniques when they improve quality, latency, cost, or reliability. What We Are Looking ForHands-on experience building LLM-powered features that shipped to real usersProduction engineering chops in TypeScript/Node (primary, especially in AWS Lambda) and/or PythonExperience with multiple LLM providers such as Anthropic, OpenAI, Google Vertex, AWS Bedrock, or similarPractical judgment in prompt engineering, retrieval, and agent design, backed by evaluation resultsTrack record of building evaluation systems that actually catch regressionsSolid software engineering fundamentals: you can write production code, not just notebooksTech stackTypeScript, Node.js, Python, AWS Lambda, Anthropic API, OpenAI API, Google Vertex, AWS Bedrock, pgvector, ECS FargateSeniority3 -​ 8 years of experience in hands-​on software engineering,​ building LLM-​powered features that shipped to real usersWork experienceHas shipped LLM-​powered features to real users in production at a reputable,​ high-​growth startup with a high engineering bar and can speak to what brokeBuilt agents and agentic systems -​ orchestrating LLMs,​ tool use over large data setsHas kept up with the frontier of agentic AI methods with a finger on the pulse;​ LangChain-​only experience is a yellow flagExperience on a small team (<​15 engineers) or as a founding engineer / former founder.​Enterprise vertical SaaS experienceForward Deployed Engineer -​ or explicitly customer-​facing type experienceEducationBachelor's degree in Computer Science.​ (MUST HAVE) No other technical degree will be consideredHard skillsProduction engineering chops in TypeScript/Node (primary,​ especially in AWS Lambda) and/or PythonExperience with eval systems,​ structured output,​ and function calling.​Experience with Anyscale Ray or similar distributed compute frameworks for batch inference,​ eval pipelines,​ or scaling agent workloadsOpen source contributions in the LLM or agent tooling spaceFamiliarity with pgvector or other vector retrieval systemsExperience with post-​training or fine-​tuningSoft skillsGenuinely excited about early-​stage work and the company/missionSalary$180K - $250KEquityCompetitive equityOn-site work policy5 days in-office in SOMA, San Francisco or New YorkVisa sponsorship not availableNo visa sponsorship available