THE ROLE:Are you the person on your team who builds the agent everyone else ends up using? We're looking for an AI Engineer to join our Training Product team and do that at Baseten. You'll build AI-driven product features for the customers training and post-training frontier models on our platform, and you'll raise the ceiling on how Baseten itself uses AI internally, turning manual workflows into agentic ones that make every other team faster.
You'll work directly with our research engineers to scope and build products, taking ideas from a research loop that already works internally to something customers can run themselves. This is a hands-on role with real autonomy. You'll pick the problems worth solving, build the harnesses, execution flows, and guardrails that make AI systems reliable, and own the results. If you've been shipping agents and want that to be the job, let's talk.
EXAMPLE INITIATIVES:Take a look at these blog posts written by members of our team:
- Baseten Training: an autoresearch substrate
- Introducing Baseten Loops
- Harnesses are everything. Here's how to optimize yours.
- Building with NVIDIA Nemotron 3 Ultra and LangChain Deep Agents Code on Baseten
RESPONSIBILITIES:- Build and ship agentic product experiences, including chat-style and assistant-like interfaces, from prototype to GA.
- Design the harnesses, execution flows, and guardrails that make AI systems reliable in production.
- Build internal automation and AI tooling that measurably increases the velocity of engineering, research, and go-to-market teams.
- Partner with research engineers to scope product opportunities out of internal research workflows and turn them into customer-facing features.
- Define and instrument evals so you know whether a change actually improved output quality.
- Work throughout the stack (API layer, backend, agent orchestration, frontend) to implement features end to end.
- Use Baseten's own training and inference products yourself to develop intuition around customer workflows.
- Identify where AI can replace manual process across the company and build the thing rather than write the proposal.
- Fix bugs and resolve customer issues with urgency.
REQUIREMENTS:- 5+ years of experience building and shipping software applications.
- Demonstrated experience building AI or LLM-powered products, agents, or agentic workflows that real users depend on.
- Strong software engineering fundamentals and the ability to clear a real technical bar, not just prompt well.
- Ability to build accurate mental models of how systems work under the hood, including the models and harnesses you're building on.
- Proficiency in Python, with fluency in at least one other language.
- Comfort working autonomously in a fast-moving environment with limited structure.
- Ability to move between customer-facing product work and internal tooling and automation.
- Strong communication skills, with the ability to bridge technical depth and business needs.
NICE TO HAVE:- Experience as a founding engineer or early employee at a startup.
- Experience building evals, agent observability, or tooling for non-deterministic systems.
- Familiarity with agent frameworks and harnesses (LangChain, Claude Code, Codex, OpenCode, MCP).
- Experience with model development methods like supervised fine-tuning, reinforcement learning, synthetic data generation, LoRA, and full fine-tunes.
- Frontend fluency.
BENEFITS- Competitive compensation, including meaningful equity.
- 100% coverage of medical, dental, and vision insurance for employee and dependents
- Flexible PTO policy including company wide Winter Break (our offices are closed from Christmas Eve to New Year's Day!)
- Paid parental leave
- Fertility and family-building stipend through Carrot
- Company-facilitated 401(k)
- Exposure to a variety of ML startups, offering unparalleled learning and networking opportunities.
Apply now to embark on a rewarding journey in shaping the future of AI! If you are a motivated individual with a passion for machine learning and a desire to be part of a collaborative and forward-thinking team, we would love to hear from you.
