Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
Boston DynamicsDate not stated

Atlas Research Engineer, SLAM & Spatial AI

Waltham, United States$177,000 – $225,000 a year
Who we'd reach at Boston DynamicsFound and reached by Power Apply
Best leadHiring manager

Leads the team this role joins

Team director

Heads the group this role sits in

Recruiter

In-house, owns the opening

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a research engineering role on the Atlas VLA Research team at Boston Dynamics, based at the Waltham office, for engineers who work on SLAM and spatial perception. The work covers real-time localization and state estimation that runs on the Atlas humanoid, plus offline 3D reconstruction that produces geometric data for training large vision-language-action models. The team looks for people who can combine classical geometry with learned methods and test their work on the robot often.

What you’ll do

  • Build real-time SLAM and perception-based state estimation for a mobile humanoid or data collection devices working in unstructured, changing settings.
  • Create offline reconstruction pipelines using multi-view geometry, structure from motion, multi-view stereo, neural reconstruction, and depth and pose fusion.
  • Research how to ground language and vision in 3D geometry so learned policies can reason about space.
  • Decide when to use optimization-based estimation and when to use learned representations, and combine them.
  • Write production-quality C++ and Python for a large codebase, working with perception, robotics, ML and systems specialists.

What they’re looking for

  • PhD in robotics, computer vision, machine learning, computer science or a related field, or equivalent experience.
  • Prior work building and deploying SLAM, visual odometry or 3D reconstruction systems for robots or autonomous vehicles.
  • Strong background in at least one of: real-time SLAM and visual-inertial odometry, 3D reconstruction, probabilistic state estimation and sensor fusion, or spatial representations and grounding of language and vision.
  • Solid grounding in Lie groups, nonlinear optimization and multi-view geometry.
  • Strong analytical and debugging skills, with reliable research code in C++ and Python.

Nice to have

  • PyTorch or JAX experience and an understanding of how perception output feeds large-scale training.
  • Experience building reconstruction or data pipelines that produce training data for vision or VLA models.
  • Familiarity with VLA and large behavior models and how spatial grounding helps manipulation.
  • Publications at venues such as CVPR, ICCV, ECCV, RSS, ICRA or CoRL.

What’s on offer

  • Base pay between $177,000 and $225,000 per year, set by factors such as internal equity, skills and experience.
  • Benefits include medical, dental and vision coverage, a 401(k), paid time off and an annual bonus structure.
  • Frequent hands-on testing of models on the Atlas humanoid.

Skills

SLAMvisual-inertial odometrystate estimation3D reconstructionstructure from motionmulti-view stereoneural reconstructionsensor fusionfactor graphsC++PythonPyTorchJAXcomputer visionLie groupsnonlinear optimization

Questions about this role

Where is this role based?

The role is listed at the Boston Dynamics Waltham office.

What is the pay range?

The base pay range is $177,000 to $225,000 per year. Final pay depends on factors such as internal equity, skills and experience.

Is a PhD required?

The posting asks for a PhD in a related field or equivalent experience.