Senior Machine Learning Engineer - Perception

Own ML Problem Formulation: You will turn ambiguous picking performance goals into well-posed ML problems, deciding what the model predicts, how labels and rewards are defined, what loss to optimize, and what "better" actually means. This is the core of the role.

Build the Data Engine: You will own dataset strategy end-to-end, from large-scale synthetic scene generation and distributed cloud dataset jobs to scene diversity filtering and self-supervised label generation. You will identify when the data, rather than the model, is the bottleneck, and fix it.

Train and Iterate on Large Vision Models: You will fine-tune large backbones with multiple task-specific heads, run disciplined experiments, and know both which experiment to run next and when to stop.

Own Evaluation and Verification: You will define offline metrics that predict on-robot outcomes and online metrics that help you improve performance on edge cases.

Drive Technical Excellence: As a senior member of the team, you will conduct rigorous code reviews, mentor engineers earlier in their careers, and contribute to the perception and grasping roadmap.

Hand Off Cleanly to Production: You will produce deployable models with sane latency budgets, exportable graphs, and reproducible artifacts, partnering with the engineers who own runtime integration and inference optimization rather than owning that yourself.

5+ Years of Experience in Machine Learning and Computer Vision, including models you personally carried from problem statement to measured outcome.

A track record of framing problems. You can translate high-level product requirements into specific engineering tasks and explain technical trade-offs to non-expert stakeholders.

Hands-on Experience Building Datasets at Scale: generation or collection, curation, automated quality assurance, coverage and bias analysis, and active learning to systematically close edge cases.

Rigorous Evaluation Habits: baselines, ablations, metric design, and a clear sense of when a result is real.

Expert-level Python and PyTorch skills.

Comfortable with cloud training infrastructure (GCP or AWS), Docker, and experiment tracking tools.

Professional experience with at least one of the following:

Developing and training multi-task models

Developing and training multi-modal models

Developing and training multi–view models

Self-supervised, outcome-based, or reward-driven learning.