Who are we?

Antioch is the simulation platform for physical AI. We allow teams to develop, evaluate, and generate synthetic data for their physical systems in high-fidelity cloud simulation, accelerated by 3D-native agents.

With Antioch, teams create precision-calibrated digital twins, generate testing environments, and run massively parallel simulation scenarios. By moving development out of the field and into software, Antioch drastically reduces dependence on expensive, slow, and incomplete real-world testing.

We work with leading robotics, autonomy, and perception teams to make the deployment of physical autonomous systems safer, faster, and more cost-effective.

Who are we looking for?

We’re hiring Simulation Engineers to bring real customer systems into Antioch, push the platform’s fidelity, and develop the agentic harness that enables automated simulation.

This is an early, high-ownership builder role: you’ll take ambiguous, incomplete real-world systems and turn them into validated simulations that customers can trust. You’ll work across physics, sensors, data, and tooling — often in tight loops with customers.

If you like the 0 → 1 grind and want your work to directly determine whether autonomous systems succeed in the real world, you’ll fit right in.

What you'll do

Partner directly with customers to ingest their physical systems into Antioch (robots, sensors, actuators, environments) and translate incomplete specs and messy real-world data into working simulation models.

Design and implement simulation capabilities across the stack: dynamics, contacts, actuators, environments, and especially sensors.

Build and calibrate high-fidelity models of sensing systems (cameras, lidar, radar, infrared, UV, etc.), including realistic noise, failure modes, and full-pipeline behaviors (optics/RF, ISP, DSP).

Make models performant and scalable: profile bottlenecks, reduce compute cost, and improve determinism and reproducibility.

Build internal Python tooling for calibration, testing, and repeatable customer onboarding.

Build the simulation bindings for Antioch’s agentic framework, to enable automated digital twin creation, sim environment generation, and scenario testing.

Communicate clearly with customers and internal teams about assumptions, tradeoffs, and limitations.

You'll work alongside Antioch’s founders, software engineers building cloud and orchestration infrastructure, and 3D technical artists producing simulation assets.

What we're looking for

You don't need every box checked. We're looking for strength in most of these:

Hands-on experience with robotics or hardware simulation (Isaac Sim/Lab, MuJoCo, Gazebo, PyBullet, or similar). Isaac Sim/Lab is a plus.

Experience building, calibrating, and validating simulations of one or more sensing modalities, including the underlying physics (optics, RF, timing, noise) and downstream signal processing where relevant.

Ability to port complex physical systems into simulation and reason quantitatively about sim-to-real and real-to-sim fidelity.

Strong Python skills for data analysis, automation, and tooling.

Comfort working from incomplete information, applying measurement and system identification techniques to fill in gaps, and documenting assumptions clearly.

A track record of shipping production-ready capabilities, not just prototypes.

Nice-to-haves

Non-visible sensing experience (infrared/thermal, UV, radar, lidar)

Experience developing custom measurement or calibration software and workflows

Computer vision background as it relates to sensor modeling and evaluation

Rust or C++ in addition to Python

You may be a great fit if…

You're in NYC or open to relocating

You’re a high-agency builder: you don’t wait to be told what to do, you go figure it out

You give a shit — you care deeply about what you ship and reflexively take accountability

You like the 0 → 1 environment and chose it on purpose

You balance craft and pragmatism: you push for excellence, but ship what's needed now

You're comfortable with uncertainty and love diving across the stack to solve a problem