Research Engineer, 3D Perception

Orbifold AI, Inc.

Palo Alto (CA)

Vor Ort

USD 180.000 - 280.000

Vollzeit

Vor 4 Tagen
Sei unter den ersten Bewerbenden

Eine vollständige Bewerbung in einer Minute

Maßgeschneiderter Lebenslauf und Anschreiben – versandbereit.

Schaffe es an den ATS-Filtern vorbei

Zusammenfassung

Orbifold AI, Inc. is seeking a PhD-level researcher to own the 3D reconstruction stack for embodied intelligence. You will advance 6-DoF object pose, hand and full-body pose, and multi-view tracking using synchronized capture data and 4D reconstruction approaches.

You will work with leading robotics and world model teams to push accuracy in challenging scenarios (occlusion, fast motion, reflective materials) and define verified data quality for downstream robotics applications.

Qualifikationen

  • PhD or equivalent research experience in 3D computer vision with first-author publications.
  • Experience with real capture rigs and failure modes (drift, occlusion, motion blur).
  • Strong PyTorch, scalable Ray, and understanding of label quality propagation.
  • Fast-paced applied research or startup experience encouraged.

Aufgaben

  • Own the 3D reconstruction stack end to end: 6-DoF pose, hand and full-body pose, multi-view tracking.
  • Push accuracy in occlusion, self-contact, fast motion and reflective materials.
  • Train on in-house golden datasets with motion capture and force sensing.
  • Build automated critics and metrics to catch calibration drift and label noise.
  • Define what verified means for each modality and embodiment.
  • Collaborate with partner researchers to audit labels and defend numbers.

Kenntnisse

PyTorch
Ray
Label quality

Ausbildung

PhD in 3D vision

Tools

NeRF
3D Reconstruction
Camera calibration

Jobbeschreibung

Own the reconstruction accuracy the rest of the company is built on. 3D vision research background; hand and body pose, multi-view tracking, calibration.

Orbifold AI is building the infrastructure layer for Physical AI. As intelligent systems move beyond language into the physical world, they require a fundamentally new understanding of physics, action, and interaction.

We partner with leading robotics and world model research teams to advance the foundations of embodied intelligence, enabling intelligent systems to perceive, understand, and operate in the real world.

The standards we set, and the infrastructure we build to scale them, will define the next frontier of robotics and Physical AI.

Role Overview

At the moment a hand closes on an object, the object hides the hand. That is the first blocker a single camera hits, and it runs both ways, through a task, the body and the objects it touches keep hiding each other. It is also precisely the moment a robot policy most needs to learn from. We capture from several synchronized viewpoints for this reason, and reconstruct in 4D rather than estimating depth from pixels.

You own that reconstruction. Every claim Orbifold makes to a partner rests on one thing: our labels are correct to a tolerance nobody else is hitting. Below a certain accuracy threshold the data is noise; above it, an hour of human demonstration is worth an order of magnitude more than an hour of robot teleoperation. Your work is what puts us on the right side of that line and keeps us there as the corpus grows.

This is the most load‑bearing research seat at the company. If the labels are wrong, every downstream conclusion, ours and our partners’, is wrong with them.

What You Will Work On
  • Own the 3D reconstruction stack end to end: 6-DoF object pose, hand and full-body pose, multi-view and long-horizon tracking, contact detection, temporal and physical consistency.
  • Push accuracy where it is hardest: occlusion, self-contact, fast motion, transparent and reflective materials, because that is exactly where robot policies fail.
  • Train on golden datasets captured in-house with motion capture, instrumented gloves and force sensing, and use them to prove the models are still improving.
  • Make quality measurable. Build automated critics and metrics that catch calibration drift, synchronization error, tracking failure and label noise before a customer does.
  • Define what "verified" means for each modality and embodiment, and hold that line when a delivery deadline argues otherwise.
  • Close the loop with capture. Where perception fails systematically, change how we capture, rig geometry, viewpoint placement, calibration procedure, lighting.
  • Work with partner researchers who will audit your labels and be able to defend the numbers in detail.
What We Are Looking For
  • PhD or equivalent research experience in 3D computer vision or a closely related field, with first-author publications.
  • Depth in at least one of: 6-DoF pose estimation, hand and body pose, multi-view or long-horizon tracking, neural reconstruction (NeRF, 3DGS), SLAM, camera calibration, physics-based state estimation.
  • You have worked with real capture rigs and know the many ways they fail, drift, desynchronization, occlusion, motion blur, bad extrinsics.
  • Strong PyTorch, comfortable at scale on Ray, and able to reason about how label quality propagates into downstream model performance.
  • Self-driven and high agency, with experience in fast-paced applied research or startup environments.
  • We index on the quality of the work rather than years served. A recent PhD with strong first-author publications in a directly relevant area is exactly who we want to talk to.
Nice to Have
  • Egocentric vision, hand-motion sensing, or wearable capture.
  • Multi-embodiment or contact-rich capture: humanoids, bimanual, dexterous hands.
  • Tactile or force sensing and multimodal sensor fusion.
  • Annotation tooling or human-in-the-loop quality systems at scale.
  • A benchmark or evaluation suite you authored.
Why This Role
  • The work is genuinely load‑bearing. Not a supporting function, the correctness of your stack is the company’s central claim.
  • Data most researchers never get to touch. Multi-view, contact‑rich, physically grounded capture at a scale academia cannot reach, growing every week.
  • A measurable frontier. Reconstruction accuracy is a number, ours is already good, and making it better is unambiguous progress.
  • Founding scope. You define the quality standard, and it becomes how our partners define theirs.
Hol dir deinen kostenlosen, vertraulichen Lebenslauf-Check.

oder ziehe deine Datei hierhin.

Similar jobs

Ähnliche Jobs, die dir auch gefallen könnten

Research Engineer, World Models & Simulation
Research Engineer, World Models & Simulation

Orbifold AI, Inc. • Palo Alto (CA)

Vor Ort
USD 150.000 - 210.000
Research Scientist (Spatial AI & Neural Reconstruction)
Research Scientist (Spatial AI & Neural Reconstruction)

Mecka • New York (NY)

Vor Ort
USD 150.000 - 230.000
Research Communications Lead, Physical AI
Research Communications Lead, Physical AI

Encord • London (KY)

Hybrid
USD 90.000 - 150.000
Competitive salary + equity
4 days/week culture
Annual learning & development budget
+3
Senior Computer Vision Engineer - Egocentric Perception
Senior Computer Vision Engineer - Egocentric Perception

Frontdoor Defense • Atlanta (GA)

Hybrid
USD 160.000 - 230.000
Founding Robotics Engineer, Perception & VLA
Founding Robotics Engineer, Perception & VLA

Bonfirevc • New York (NY)

Vor Ort
USD 150.000 - 210.000
Founding equity
Research Engineer
Research Engineer

Human Archive • San Francisco (CA)

Vor Ort
USD 100.000 - 140.000
Machine Learning Engineer: Perception
Machine Learning Engineer: Perception

Bedrock Robotics Inc • San Francisco (CA)

Vor Ort
USD 120.000 - 160.000
Research Engineer, Physical AI (Robotics, World Models)
Research Engineer, Physical AI (Robotics, World Models)

Orbifold AI • Palo Alto (CA)

Vor Ort
USD 180.000 - 240.000
Research Scientist — 3D Reconstruction & Spatial AI
Research Scientist — 3D Reconstruction & Spatial AI

Tera AI • San Francisco (CA)

Vor Ort
USD 130.000 - 190.000
Machine Learning Engineer (Egocentric 3D Human Pose)
Machine Learning Engineer (Egocentric 3D Human Pose)

Glint Tech Solutions LLC • USA

Remote
USD 120.000 - 180.000
Competitive salary and equity package
Medical, dental, and vision insurance
401(k) retirement plan
+4