SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Apptronik is a Series B human-centered robotics company developing AI-powered humanoid robots (Apollo) to support humanity across manufacturing, logistics, healthcare, and beyond. The company operates at the cutting edge of applied AI, tackling the full robotics stack from research to production.
As Principal Robotics Machine Learning Engineer, you will be a core technical contributor responsible for the end-to-end lifecycle of learned manipulation—from data engine design through model training to on-robot deployment. You will diagnose performance bottlenecks, bridge cutting-edge research with scalable production software, and operate with high ownership and low bureaucracy in a startup environment.
Key responsibilities include:
- Implementing and deploying state-of-the-art ML models and algorithms for open-world object manipulation tasks on physical hardware, achieving world-class performance.
- Driving the data engine for manipulation learning: designing data collection strategies, curation, annotation, and managing the synthetic/real data mix in partnership with data infrastructure teams.
- Owning the entire development cycle from simulation prototyping to robust model transfer and fine-tuning on the robot.
- Identifying and prioritizing performance bottlenecks, distinguishing root causes in classical vision (calibration, geometry, sensor fusion) versus model/data optimization, and prioritizing fixes to meet customer reliability expectations.
- Acting as a force multiplier across the organization through code reviews, fostering technical rigor, setting architectural standards, and mentoring the next generation of robotics leaders.
You will need deep fluency in both classical computer vision and modern deep learning to unlock the full potential of state-of-the-art humanoid robot hardware.
REQUIREMENTS:
Must-Have Technical Skills:
- 5+ years shipping machine learning models on robotic systems in production environments
- Expertise in AI models 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
Education & Experience:
- BS/MS/PhD in Robotics, Computer Science, Electrical Engineering, or related field
- 7+ years relevant experience (or 5+ years with a PhD) specifically in robotic manipulation or complex motion control
- Proven track record of taking complex algorithms from conception to successful deployment on physical hardware
Good to Have:
- MLOps familiarity (distributed training, MLOps principles)
- Experience with VR/haptic interfaces and retargeting algorithms for human-in-the-loop control
- Experience with physics engines (IsaacSim, MuJoCo, Drake) for policy training and validation
- Background in logistics automation using manipulators for dynamic material handling tasks
