What are the responsibilities and job description for the Robotics/Physical AI Manipulation Engineer position at Autonomique?
About Autonomique
Autonomique is a startup building at the forefront of Physical AI: making robots do real work in the real world. Our intelligence framework solves the core challenges of autonomy—perception, reasoning, and dexterity—to empower reliable operations for the world’s most demanding industries. We're already deploying bimanual semi—humanoid robots at Tier-1 automotive and biopharma manufacturers.
The Position
We are looking for talented, hands-on engineers and researchers to help us push the boundaries of what our autonomous robots can do. You will work to improve how our robots perceive the world and manipulate objects within it. Your code will run on real hardware in challenging environments where speed and precision matter.
What You’ll Do
- Deploy Robust Manipulation Algorithms: Design and implement algorithms for complex bimanual tasks (pick/place, insertion, tool use) that don't just work in the lab but perform reliably in dynamic industrial environments.
- Fine-tune Manipulation Models for Robustness, Precision and Speed: Collect tele-op data and train policies that hold up under real-world variation (object pose, lighting, occlusion, wear), hit tight tolerances (sub-mm insertion, force-sensitive grasps), and meet production cycle-time targets.
- Real-World Perception & Control: Write and refine controllers and perception stacks (including 6D pose estimation) for immediate deployment on physical robots.
- Ship State-of-the-Art Models: Collaborate with Software engineers to take research models and optimize them for production constraints (latency, safety, failure recovery).
Must Haves
- Educational Background: MS or PhD in Robotics, Computer Science, or a related field.
- Manipulation Experience: You have built projects or done research involving robotic arm control with learning based models such as VLA, Diffusion Policy, Flow matching, and RL on a physical robot.
- Trained and Deployed Manipulation models for contact-rich tasks with force feedback.
- Coding: Strong proficiency in Python; C is a bonus.
- ML Frameworks: Deep understanding of PyTorch.
- OS: Ubuntu or related Linux.
Bonus Points
- Experience with ROS/ROS2.
- Vision Skills: Familiarity with computer vision and pose estimation frameworks
- Hands-on experience with real robotic hardware (not just simulation).
- Hands-on "hacker" experience: you aren't afraid to debug a loose wire or calibrate a camera yourself.
- First-author publications at top-tier conferences (ICRA, CoRL, RSS, CVPR, NeurIPS).
- Published code or projects we can look at (GitHub).
Why Join Us
- Ownership: We offer a substantial equity package designed for those who believe in our mission and want to be rewarded for the company's long-term success.
- Impact: Work directly on real-world projects and see your code deployed in the real world immediately. We are already shipping robots in production.
- Culture: A collaborative, high-velocity supportive environment conducive to both personal and professional growth.
Logistics
- Location: Menlo Park, California (On-site)
- Start Date: Flexible.