Software Engineer, Locomotion

Galactic Resource Advancement Mechanism Technologies Corporation•El Segundo, CA

5d•Onsite

About The Position

GRAM is a Self-Replication (SR) company creating machines that reproduce, with the first goal being survival without humans. We challenge the consensus that robots should look or act like us and reject the claim that single-agent task-generality is the only way forward. We believe there exists a scaling law for machine labor and are looking for individuals to contribute to frontier problems on hardware that will touch every industrial substrate known to man. Our mission is to make humanity galactic. The role focuses on Self-Traversal, the locomotion problem of moving across any surface, in any gravity, of any geometric complexity, with no prior assumption about what the robot will find beneath its feet. This is a foundational capability for all GRAM hardware. The technical approach is inspired by biology, utilizing a multi-legged platform for redundant grasp, RL-trained policies for complex contact schedules, vision-coupled control for perception-based foothold selection, and gravity-agnostic operation.

Requirements

Demonstrated work in robot locomotion: research output, hardware deployment, open-source contribution, or production system.
Evidence of a learned policy you have personally taken from simulation onto physical hardware, at any scale.
Working fluency in Python and at least one modern legged-robot stack: Isaac Lab, legged_gym, rsl_rl, MuJoCo (MJX or MuJoCo MPC), Drake, Pinocchio, OCS2, or Crocoddyl.
Foundational understanding of modern RL (PPO, SAC, off-policy methods) and classical contact mechanics.
Pure-simulation RL with no hardware deployment is disqualifying.
Pure-MPC backgrounds with no exposure to learned policies are disqualifying.

Nice To Haves

MS in Robotics, CS, Mechanical, or Electrical Engineering preferred for production candidates and waivable for strong artifact evidence.
C++ proficiency expected for production candidates and welcome to develop for early-career applicants.
PhD focus on legged locomotion, learned control, or contact-rich robotics, with publications at RSS, CoRL, ICRA, IROS, NeurIPS, ICML, or ICLR.
Direct lineage from one or more of: ETH RSL, MIT Improbable AI, Berkeley Hybrid Robotics, Stanford IPRL, NVIDIA Isaac, Oxford ORI, CMU LeCAR, UCSD (Wang lab), JPL LEMUR / Parness, Cutkosky / BDML at Stanford, Ramezani at Northeastern, Penn Kodlab, KAIST CLS.
Vision-conditioned locomotion experience: footstep selection conditioned on RGB, depth, or event cameras rather than elevation maps.
Non-planar contact experience: climbing, inversion, microspine or gecko-adhesion grippers, asteroid-surface mobility, or any setting where the gravity vector relative to the body is not constant.
Familiarity with whole-body contact-rich analytical control (TSID, Pinocchio, OCS2, Crocoddyl).
The stack may layer analytical contact-force regulation under the learned policy at the gripper interface.

Responsibilities

Own the Self-Traversal locomotion policy end to end, including training in simulation, deployment on hardware, and closing the sim-to-real gap on a contact-rich, non-planar platform.
Design contact-aware RL training environments and curricula for arbitrary 3D structure, with domain randomization across surface geometries, contact mechanics, and gravitational orientations.
Architect the vision-coupled footstep-selection stack so next-foothold decisions are conditioned on raw perception of arbitrary geometry rather than precomputed elevation maps.
Co-design with mechatronics and adhesion teams to ensure the controller exploits the gripper, microspine, or compliant-foot mechanism.
Extend Self-Traversal to multi-robot configurations, enabling several robots to co-occupy a single structure and deconflict overlapping coverage in real time without central planning.