Principal Robotics Machine Learning Engineer

About the role

Apptronik is a human‑centered robotics company developing AI‑powered robots to support humanity in every facet of life. Our flagship humanoid robot, Apollo, is built to collaborate thoughtfully with people, starting with critical industries such as manufacturing and logistics, with future applications in healthcare, the home, and beyond. The Principal Manipulation Engineer is a core contributor to our robot’s ability to interact with the world with human‑like world model context, dynamic perception, and interactive behavior, bridging cutting‑edge research and scalable, reliable production software.

Responsibilities

• Implement and deploy state‑of‑the‑art ML models/algorithms to achieve world‑class performance on open‑world object manipulation tasks with physical hardware.
• Drive the data engine for manipulation learning: data collection strategy, curation, annotation, and synthetic/real data mix, in close partnership with data infrastructure teams.
• Lead the entire development cycle, from prototyping in simulation to robustly transferring and fine‑tuning models on the robot.
• Identify and prioritize performance bottlenecks, distinguishing root causes in classical vision (calibration, geometry, sensor fusion) versus sub‑optimal model/data, and prioritize fixes to meet reliability expectations.
• Act as a force multiplier across the organization: conduct code reviews, foster a culture of technical rigor, set architectural standards, and mentor the next generation of robotics leaders.

Requirements

• 5+ years shipping machine learning models on robotic systems in production environments.
• Expertise in AI model development, including CNNs and transformers.
• Proficiency in Python, C++, and PyTorch, with experience building real‑time robotic software stacks.
• Experience with data collection, annotation, and synthetic data generation for ML.
• Familiarity with 6D pose estimation, camera calibration/extrinsics, point‑cloud processing, and visual‑servoing.
• Experience with initial calibration and tuning of high‑DOF robotic manipulators.
• Good to have: familiarity with distributed training and MLOps principles.
• Good to have: experience with VR/haptic interfaces and retargeting algorithms for human‑in‑the‑loop control.
• Good to have: experience with physics engines such as IsaacSim, MuJoCo, or Drake for policy training and validation.
• Good to have: background in logistics automation using manipulators for dynamic real‑world material handling tasks.

Qualifications

• BS/MS/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 track record of taking complex algorithms from conception to successful deployment on physical hardware.

Physical Requirements

• Prolonged periods of sitting at a desk and working on a computer.
• Ability to lift up to 15 pounds occasionally.
• Vision sufficient to read printed materials and a computer screen.
• Hearing and speech to communicate effectively.