Full-Stack Robotics & AI Engineer

Astera Institute • Emerybille, CA

9d • Onsite

About The Position

Astera Institute is building a frontier robotics lab focused on embodied intelligence and the shared challenges faced by animals and robots, including perception, navigation, manipulation, memory, and reasoning. The lab aims to make robots useful in real environments while developing a mechanistic understanding of how neural circuits can generate intelligent behavior.

The Full-Stack Robotics & AI Engineer will take learning-based robotics systems from model development to reliable operation on physical robots. The role spans perception, policy learning, inference, and robot integration, connecting model predictions to robot behavior. Based in Astera’s Robotics Lab in Emeryville, California, the engineer will collaborate closely with researchers and hardware engineers to develop manipulation capabilities, investigate failures on real robots, and improve software and models together.

Requirements

• Strong Python skills.
• Practical experience training or fine-tuning models in PyTorch or a comparable framework.
• Experience integrating learning or perception systems with physical robots, including coordinate frames, sensor calibration, and action or control interfaces.
• Ability to profile software, identify runtime bottlenecks, and debug problems spanning models, robotics software, and hardware.
• A record of building working systems and evaluating them on real tasks, with a clear understanding of personal technical contributions.
• Comfort working closely with researchers and engineers, making practical tradeoffs, and iterating from experimental results.

Nice To Haves

• Experience with robot learning frameworks such as LeRobot or openpi, imitation learning, or vision-language-action models.
• Experience with model distillation and inference optimization using tools such as ONNX or TensorRT.
• Experience in dexterous or contact-rich manipulation, asynchronous policy execution, or reusable robot skill interfaces.

Responsibilities

• Develop models for robotic manipulation, including fine-tuning and evaluating vision and action models using pretrained models and robot data.
• Build software connecting cameras and other sensors to model inference and robot commands, including calibration, coordinate transforms, action representations, and control interfaces.
• Deploy models on robot hardware and optimize inference latency, memory use, and throughput through profiling, distillation, compilation, and precision changes.
• Implement responsive policy execution, including asynchronous inference and action chunking where appropriate.
• Debug failures across observations, model outputs, middleware, and physical motion; build logging, replay, and evaluation tools to understand failures.
• Package robot capabilities with clear interfaces, reproducible configurations, and tests so other team members can use and extend them.

What This Job Offers

• Job Type: Full-time
• Education Level: No Education Listed