Robotics Machine Learning Engineer

Ixian Robotics is building intelligent machines to reindustrialize America. We are based in San Francisco and backed by a16z and Accel.

We believe robotics is a full-stack problem. Software, hardware, and machine learning are only part of it. Bridging advances in robot learning with America's industrial base requires invention in how we understand customers, design products, navigate supply chains, and make the economics work. We are building a company that takes responsibility for all of it.

At Ixian, deployment is not the final step after the "real innovation" is complete. Deploying robots is the point of robotics, and deployment is our forcing function for innovation. Putting a machine to work reveals what the lab cannot: what breaks, what matters to the people using it, and what it will take to make our machines indispensable.

Robots are called machines when they work. We intend to build machines.

THE OPPORTUNITY

You will develop and train models that make robots useful on physical tasks. You will work across model development, training infrastructure, data curation, and evaluation, with direct responsibility for understanding how a change affects behavior on hardware.

The work involves choosing a useful experiment, implementing it, and finding out what the result actually means. When performance stalls, you will investigate the model, the data, and the surrounding system. You will work with software and hardware engineers to separate those causes and decide what to change next.

WHAT YOU'LL DO

• Train and fine-tune models for robotic perception and behavior, selecting approaches suited to the task and available data


• Turn research ideas into working implementations; compare architectures and training methods through controlled experiments


• Curate datasets, investigate data quality, and measure how changes in the training data affect performance


• Build evaluations with clear success criteria, repeatable procedures, and regression tracking across model versions


• Run models on physical robots, inspect failures, and work with engineering teams to improve reliability


• Maintain reproducible training workflows, including data loading, experiment tracking, and efficient use of compute

YOU SHOULD HAVE

• Experience training deep learning models and explaining the decisions behind your experiments


• Strong Python and practical proficiency with PyTorch, JAX, or an equivalent framework


• Depth in robot learning or a closely related area such as computer vision, multimodal learning, or sequential decision-making


• Careful experimental judgment: useful baselines, meaningful comparisons, and an understanding of what limited evaluation data can establish


• The ability to debug training code, inspect datasets, and work directly with physical systems to test your conclusions

NICE TO HAVE

• Experience deploying learned policies on robots


• Experience with imitation learning, reinforcement learning, or vision-language-action models


• Experience with distributed training or building evaluation infrastructure

COMPENSATION AND BENEFITS

Base Salary: $150,000 - $200,000 annually

In addition to base salary, you may be eligible for equity. Benefits include medical, dental, and vision coverage.