Member of Technical Staff, Deeptune Environments

About the Role

You'll build the systems our high-fidelity simulation environments run on, the APIs and tool interfaces agents interact with, the grading layer that decides whether an agent actually succeeded, the pipelines that turn raw human demonstrations into training-ready environments, and the orchestration and sandboxing that run it all at scale.

You'll do this alongside researchers who own the RL side. Your job is to make their ideas real: fast, correct, and reliable at scale. That means you should know enough about post-training, evals, and reward modeling to push back on a research spec productively. It does not mean you'll be training models.

The work is high-ownership and lightly specified. You'll set direction, drive outcomes, and stay hands-on. You'll also work directly with AI labs and enterprise partners, which means shipping against real external deadlines rather than internal ones.

What You'll Do

• Build the systems that build environments end-to-end: the simulated app or system, the agent-facing tool surface, the task definitions, and the verifiers that score them.
• Design and operate the backend infrastructure that runs environments at scale (containers, orchestration, queues, observability) - standard distributed-systems backend work, applied to a new domain.
• Turn messy human data into clean, reproducible training environments.
• Care about reliability and speed as much as correctness.
• Own the interface with labs and researchers: translate a research goal into a system that exists next week.

What We're Looking for

We care more about what you've built than how long you've been building it.

• 2+ years of full-stack / backend engineering, including at least 1 year at a startup, ideally as a founding engineer, an early engineer at a fast-growing venture, or a founder yourself
• Strong generalist with systems depth. We primarily use Python and seek engineers who are fluent in at least one language. Ideally, they should be skilled at applying agents with discernment and able to quickly adapt to different problem requirements.
• Comfortable around ML/LLM concepts. Not an ML background, but enough working knowledge of post-training, evals, and reward modeling to partner with researchers and translate their specs into systems.
• Thrives in ambiguity. You scope your own work, make pragmatic calls, and ship without a spec handed to you.
• Ability to raise the bar around you. Coaching engineers and driving execution, while staying in the code

Bonus, not required

sandboxing or virtualization, browser and computer-use automation, CI/build systems, developer tooling.

You'll Fit Here If

• Ownership, impact, and building frontier tech are what motivate you
• Your work is a craft you want to master
• You thrive in ambiguity and like hard problems
• You appreciate diverse perspectives and uncommon ideas
• You're excited to build in person, 5 days a week, 10 am-8 pm ET, from our office at One World Trade