20 hours ago
Responsibilities
- Implement and deploy machine learning models and algorithms for open-world object manipulation on physical robotic hardware.
- Drive manipulation-learning data strategy, including collection, curation, annotation, and synthetic-to-real data mixes.
- Develop the full lifecycle from simulation prototypes through model transfer, fine-tuning, and deployment on robots.
- Diagnose performance bottlenecks involving computer vision, calibration, geometry, sensor fusion, models, and data.
- Support hardware bring-up through calibration and tuning of high-degree-of-freedom robotic manipulators.
- Promote technical rigor and architectural excellence while mentoring robotics engineers and leaders.
Requirements
- 5+ years shipping machine learning models on robotic systems in production environments.
- Expertise with CNNs and transformers.
- Proficiency in Python, C++, and PyTorch, including real-time robotic software development.
- Experience with machine-learning data collection, annotation, and synthetic-data generation.
- Familiarity with 6D pose estimation, camera calibration and extrinsics, point-cloud processing, and visual servoing.
- Experience calibrating and tuning high-degree-of-freedom robotic manipulators.
- Familiarity with distributed training and MLOps principles is preferred.
- Experience with VR or haptic interfaces and retargeting algorithms is preferred.
- Experience with IsaacSim, MuJoCo, or Drake for policy training and validation is preferred.
- Experience automating dynamic real-world material-handling tasks with manipulators is preferred.
- BS, MS, or PhD in Robotics, Computer Science, Electrical Engineering, or a related field.
- 7+ years of relevant experience, or 5+ years with a PhD, focused on robotic manipulation or complex motion control.
- Proven ability to take complex algorithms from conception through deployment on physical hardware.
Benefits
- This is a direct-hire position.
- The role requires prolonged desk and computer work, occasional lifting of up to 15 pounds, and the ability to read screens and communicate.
Categories
ML EngineeringRobotics
About Apptronik
Apptronik designs and manufactures AI-enabled humanoid robots, led by its Apollo platform, to automate tasks alongside people in manufacturing and logistics, with potential use in healthcare and homes. The privately held company is headquartered in Austin, Texas, and grew out of the University of Texas at Austin’s Human Centered Robotics Lab; its team previously worked on NASA’s Valkyrie robot. Apptronik’s business model centers on selling robots and the software and services needed to deploy them in industrial environments.