Simulation Infrastructure Engineer

OpenAI•San Francisco, CA

1d•$230,000 - $385,000•Hybrid

About The Position

We are hiring a Sim Infrastructure Engineer to turn simulation systems into reliable, automated, production-quality pipelines that power model training, evaluation, and hardware-in-the-loop validation. This role owns the automation, orchestration, and tool integration that apply simulation to concrete robotics tasks: building CI/CD for SIL/HIL, presubmit checks, automatic model evaluation, metric computation and reporting, and the runtime infrastructure to run simulations at scale. You will collaborate closely with Sim Realism, Sim Environments, Research, and Ops to make simulation an integrated, reproducible, and measurable part of our ML and robotics workflows. This role is based in San Francisco, CA, and requires in-person 4 days a week.

Requirements

Deep software engineering & infra experience: you’ve built CI/CD at scale, authored reliable pipelines, and shipped production services that coordinate many moving parts.
Comfortable with distributed compute and cloud GPU workloads: you know how to get many sims running concurrently (scheduling, batching, GPU orchestration) and optimize throughput/cost.
Built or maintained HIL/SIL workflows or other sim↔hardware integrations and understand the operational challenges of bridging software and hardware testbeds.
Strong with automation, observability and metrics: you enjoy instrumenting systems, defining meaningful KPIs, and surfacing regressions early.
Can design APIs and developer ergonomics so research and SWE teams can easily submit jobs, reproduce experiments, and interpret results.
Experience with Python/C++/Rust, container orchestration (Kubernetes), distributed task queues, and CI systems
Enjoy collaborating across teams to turn experimental simulation work into dependable production tooling.

Nice To Haves

Bonus if you’ve worked with RL tooling, task generators, or large-scale data pipelines.

Responsibilities

Build and maintain presubmit checks, continuous integration and deployment pipelines for simulation code, environments, and tasks so simulation artifacts are testable, versioned, and reproducible.
Implement end-to-end automation to run model evaluation in sim (SIL) and orchestrate HIL runs; compute realism and task metrics, generate dashboards and alerts, and ensure evaluation is repeatable and auditable.
Create robust APIs and connectors so research, training, and data-collection systems can schedule, seed, and evaluate batches of simulations; support RL rollouts, imitation-data collection, and presubmit model checks.
Build scheduling, batching and orchestration for running very large numbers of concurrent rollouts (target tens of thousands of rollouts / large RL workloads), solve engine-level scaling (parallelization, batching multiple runs per engine), and optimize cloud/GPU runtime reliability.
Produce metrics and tooling for measuring simulation health, throughput, fidelity regressions, and cost; create presubmit / canary tests that catch sim regressions early.
Implement artifact versioning, environment immutability (images / asset versions), experiment provenance, and policies for resource quotas and cost control across the sim farm.
Work closely with Sim Environments, Sim Realism, research, and ops to close the loop—ensuring simulation improvements directly translate into better model evaluation and training results.