Senior Machine Learning Engineer - Perception

Pickle Robot Company is hiring a Senior Machine Learning Engineer focused on perception and grasping systems in Charlestown, MA. In this onsite role, you will own perception-related machine learning work end-to-end, with a modeling loop that includes defining the problem, building the data engine, running training and experiments, and validating performance.

Pickle Robot Company’s engineering team splits responsibilities so you can concentrate on learning and evaluation while platform and robotics engineers handle runtime integration and edge deployment.

What you’ll do

• Own ML problem formulation: translate unclear picking performance goals into well-posed ML tasks by deciding targets, label and reward definitions, optimization objectives, and what “better” means in practice.
• Build and operate the data engine: lead dataset strategy from large-scale synthetic scene generation and distributed cloud dataset jobs to scene diversity filtering and self-supervised label generation.
• Fix bottlenecks in the data: identify when improvements depend on dataset quality and coverage rather than model changes, then implement the corrective work.
• Train and iterate on large vision models: fine-tune large backbones using multiple task-specific heads, run structured experiments, and develop strong judgment on the next experiment and stopping criteria.
• Own evaluation and verification: create offline metrics that track on-robot outcomes and define online measurement approaches to improve performance on edge cases.
• Drive technical excellence: lead rigorous code reviews, mentor engineers earlier in their careers, and contribute to the perception and grasping roadmap.
• Hand off cleanly to production: deliver deployable models with practical latency budgets, exportable graphs, and reproducible artifacts, collaborating with the engineers responsible for runtime integration and inference optimization.

What you bring

• 5+ years of experience in machine learning and computer vision, including taking models from problem statement through measured outcomes.
• A proven ability to frame problems into actionable learning objectives.
• Hands-on dataset experience at scale: generation or collection, curation, automated quality assurance, coverage and bias analysis, and active learning to systematically address edge cases.
• Strong evaluation habits: use baselines and ablations, design metrics, and know when results are truly meaningful.
• Expert-level Python and PyTorch.
• Comfort with training and tooling: cloud training infrastructure (GCP or AWS), Docker, and experiment tracking tools.
• Professional experience with at least one: multi-task models, multi-modal models, multi-view models, or self-supervised, outcome-based, or reward-driven learning.

Technology

• Python
• PyTorch
• GCP
• AWS
• Docker

Compensation and location

• Location: Charlestown, MA (onsite)
• Salary: USD 170,100 - 227,400 per year

Benefits

• Health, dental, and vision insurance
• Unlimited vacation
• Paid federal and state holidays
• 401(k) contributions of 5% of your salary
• Company-covered travel expenses
• Additional perks to support comfort and productivity

AI tools notice

• Pickle Robot Company may use AI tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals.
• AI tools support the recruitment team but do not replace human judgment.
• Final hiring decisions are made by humans.
• If you want more information about how data is processed, contact the company.