Skip to content

Development

Data Scientist

We're hiring a Data Scientist with deep experience in video analytics, action understanding and multimodal sensor data — someone who can turn hours of egocentric footage into measurable dataset quality.

Full-timeTashkent, Uzbekistan

The Role

This role sits at the core of our product: extracting signal from chaotic, real-world sensor streams.

You will own how we measure and improve our datasets — from sensor synchronization and hand-pose quality to action boundaries and task coverage — and turn those measurements into tools the capture and annotation teams use every day.

You will be shaping how humanoids and manipulators learn from human demonstrations across factories, warehouses, hospitality sites, and more.

What You'll Do

  • Analyze multimodal recordings (stereo RGB-D, IMU, hand and body pose) to find failure modes, drift and noise before they reach a customer.
  • Build and maintain our quality metrics and golden benchmarks — the ground truth that automatic chunking, action labeling and pose stages are scored against.
  • Develop segmentation, temporal-alignment and quality-filtering methods that feed our processing pipeline.
  • Create internal dashboards and tools for dataset health, annotator throughput and per-session scoring.
  • Prepare model-ready exports (MCAP, HDF5, RLDS, LeRobot) and document exactly what is in them.
  • Stress-test assumptions: what signals matter? What can be thrown away? What's actually learnable?

Who You Are

  • You think in systems, not notebooks.
  • Strong in Python, PyTorch, CV/ML, and familiar with robotics-adjacent tooling (ROS, teleop systems, sensor sync).
  • Comfortable with bad data, missing timestamps, corrupt frames and noisy sensors — and extracting order from them.
  • Prefer measurable impact over academic elegance; skeptical of magic-model thinking.
  • Bonus: experience with imitation learning (ALOHA, ACT-style models), action segmentation, or multimodal transformer pipelines.

Why Humaid

  • Work directly on the bottleneck of Physical Intelligence — real-world data.
  • Your metrics decide what ships: every dataset we deliver is scored against the benchmarks you build.
  • Fast, practical team that actually deploys — not a research museum.
  • Competitive salary plus the everyday perks that matter — sports and wellness memberships, team events, and the equipment you need to do your best work.

How to Apply

Send your CV to career@humaid.co with the role title in the subject line.

Links to your GitHub, portfolio or publications are welcome.

Apply now