About Us
At Pickle Robot, we're on a mission to automate global supply chains with Physical AI. Our robots work alongside warehouse teams to unload trucks and containers — one of the toughest, most understaffed jobs in logistics — making the work safer, faster, and more efficient for the people doing it. Loading trucks comes next, followed by the Dill Autonomy Engine: generalized autonomy that will eventually orchestrate robots across entire logistics processes.
We're looking for a rigorous and self-directed Senior Machine Learning Engineer to own machine learning problems end-to-end on the systems that decide how our robots grasp packages. This role will focus on problem formulation, building the data engines that feed our models, training and experimentation, and the evaluation rigor that tells us whether a model is genuinely better. Our platform and robotics engineers own runtime integration and edge deployment, so you can stay focused on the modeling loop.
What You'll Do
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 data, rather than the model, is the bottleneck and fix it.
Show the full description
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 let 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.
- What You'll Bring
- 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.
