Machine Learning Engineer

Watney is hiring a Machine Learning Engineer in San Francisco, CA (onsite) to build and improve models using data from a live fleet of robots.

Responsibilities

• Run and evaluate training experiments as model capability scales.
• Curate and clean the datasets used for experiments.
• Contribute to evolving approaches for labeling and structuring new data.
• Track and analyze performance metrics to distinguish models that help from those that do not.
• Partner with Teleoperations to understand and improve data at its source.

Requirements

• Experience training models on real-world data collected from actual robot operation.
• Experience with imitation learning, reinforcement learning, or a comparable control-focused method.
• Ability to write production machine learning code in Python and PyTorch (or equivalent tooling).
• Comfort working with and cleaning messy, real-world datasets.

Technologies

• Python
• PyTorch

About the role

• At Watney, machine learning engineers improve a live robot fleet by turning field data into models that perform better on the next deployment.
• The fleet generates substantial real-world video, and converting that stream into reliable model performance is a core challenge.
• Model development covers multiple task types, including what the robot sees, decides, and acts on.
• Work is staged from imitation learning toward broader generalization, combining experiment execution, dataset curation and labeling, and evaluation on the real fleet.

Mission

• Expand human ambition in the physical world.

Additional fit signals

• Trained models using real-world operational data.
• Worked with imitation learning, reinforcement learning, or similar control methods.
• Writes production ML code in Python and PyTorch.
• Comfortable cleaning and curating messy, real-world data.

To learn more, follow Watney on X and LinkedIn.