Embodied AI​/Simulation Engineer San Francisco Oakland, CA

Formic is on a mission to reshape American manufacturing by making automation accessible to every factory. As labor constraints rise, costs increase, and global competition intensifies, automation is no longer optional for manufacturers that want to stay competitive.

We deliver automation through a Robotics-as-a-Service model that combines industrial robotics, proprietary software, and full-service support into a single, integrated solution. By removing the traditional barriers of cost, complexity, and risk, we enable manufacturers to deploy automation quickly and realize measurable gains in throughput, safety, and operational efficiency without large upfront capital investment.

Backed by leading investors including Lux Capital, Initialized Capital, Blackhorn Ventures, and Mitsubishi HC Capital North America, Formic is scaling rapidly and building the foundation for a new era of high-performance, Made in America production.

The Software Engineering Team builds and operates the systems that power Formic’s Robotics-as-a-Service platform.

Engineering focuses on ensuring deployed systems are observable, resilient, and remotely diagnosable  team builds production-grade edge and cloud systems that support reliable data collection, remote troubleshooting, live video streaming, and continuous system improvement.

This work directly impacts fleet uptime, service efficiency, and customer outcomes by ensuring Formic’s monitoring and control infrastructure remains scalable, reliable, and continuously evolving.

As an Embodied AI / Simulation Engineer, you will develop learning-based manipulation systems for humanoid and mobile manipulation platforms and ensure they transfer reliably into the real world. You will build the simulation, data, and training infrastructure needed to develop robust visuomotor policies and deploy them onto physical robotic systems operating in production environments.

This role sits at the intersection of simulation, machine learning, and robotics execution. You will work closely with perception and controls teams to ensure learned policies operate safely, reliably, and effectively in closed-loop real-world conditions.

• Design, train, and evaluate learning-based manipulation policies for humanoid and mobile manipulation platforms
• Develop and maintain high-fidelity simulation environments and digital twins using Isaac Sim, Mu Jo Co , or similar tools
• Implement and benchmark approaches including Action Chunking with Transformers (ACT), diffusion policies, behavior cloning, and Vision-Language-Action (VLA) models
• Contribute to a Universal Manipulation Interface (UMI) abstraction layer that standardizes policy inputs, outputs, and deployment interfaces
• Build scalable teleoperation-to-training data pipelines, including tooling for dataset generation, curation, and labeling
• Design and execute sim-to-real transfer strategies including domain randomization, system identification, and calibration workflows
• Analyze policy robustness, failure modes, safety constraints, and cross-task generalization in closed-loop settings
• Partner with perception and controls teams to integrate learned policies with real-time systems and ensure stable execution
• Deploy trained models onto physical robots and lead on-hardware validation, debugging, and iteration
• Establish experimental rigor through structured evaluation plans, ablations, reproducible training runs, and performance tracking

• Demonstrated experience training embodied AI policies that run on real robotic systems
• Strong understanding of sim-to-real transfer challenges, hardware constraints, and real-world failure modes
• Familiarity with transformer-based action models such as ACT
• Experience with diffusion policies or other generative approaches for control and decision-making
• Experience working with multimodal inputs including vision, proprioception, and language
• Proficiency in Python and deep learning frameworks such as PyTorch or JAX
• Experience integrating learned policies with real-time control stacks and deployment environments
• Strong experimental design and evaluation discipline, with…