Machine Learning Engineer

About the role

At Watney, ML engineers turn a live fleet of robots into better models. The fleet produces large volumes of video from real work in the field, and turning that data into a model that performs better on the next deployment is one of the hardest problems at the company. The model work spans multiple kinds of tasks: what the robot sees, decides, and acts on. You will help decide the path forward, staged from imitation learning toward broader generalization: run training experiments, help curate and label the data behind them, and help evaluate what works on a real fleet.

Responsibilities

• Run and evaluate training experiments as we scale our models.
• Curate and clean the data those experiments train on.
• Help evolve how we label and structure new data.
• Track the metrics that separate a model that helps from one that doesn't.
• Work with Teleoperations to understand and improve the data at its source.

Requirements

• Have trained models on real-world data pulled from actual operation.
• Have worked with imitation learning, reinforcement learning, or a similar method for control.
• Write production ML code (Python, PyTorch, etc).
• Are comfortable cleaning and curating messy, real-world data.