Qualifications
Key Responsibilities
Develop end-to-end learning-based manipulation models for sensor-driven interactions (e.g., reaching, motion generation, execution in dynamic contexts).
Construct and maintain manipulation training pipelines, including dataset creation, action representations, data augmentation, and distributed training.
Design robust evaluation metrics and regression tests to quantify manipulation reliability, recovery behavior, and safety in real-world scenarios.
Create sim-to-real workflows for manipulation learning, encompassing simulation environments, domain randomization, and failure-mode testing.
Optimize models for edge deployment, benchmarking latency, memory usage, and stability on target hardware.
Collaborate with the AI platform team to integrate policies with control and safety systems, and validate end-to-end robot performance.
Analyze field performance, identify failure modes, and drive improvements through data collection and targeted retraining.
Basic Qualifications
Bachelor’s or Master’s degree in Robotics, Computer Science, Electrical Engineering, or a related field (PhD preferred).
3+ years of experience in applying machine learning to robotics manipulation, visuomotor control, or sequential models.
Strong proficiency in PyTorch with experience in building reliable training and evaluation pipelines.
Excellent software engineering skills in Python, with a collaborative spirit to work across ML and robotics teams.
Preferred Qualifications
Experience with Vision-Language-Action (VLA) models, behavior cloning, or similar methodologies.
About the job
Join Us in Revolutionizing Robotics!
Diligent Robotics envisions a future where robots and humans work hand-in-hand in seamless collaboration. Our cutting-edge artificial intelligence empowers service robots to interact dynamically with human environments. As part of our mission-driven team, you will contribute to the design and development of both current and next-generation robots.
In the role of Machine Learning Engineer II (Manipulation), you will spearhead the creation and deployment of learning-based manipulation systems, enabling our mobile robots to interact reliably within dynamic human settings. Your contributions will include developing perception-to-action models, assembling training datasets, creating evaluation tools, and establishing deployment pipelines that enhance robustness, generalization, and safety for real-world manipulation tasks. Your work will be pivotal in ensuring our robots execute complex interactions consistently across diverse environments without the need for specialized engineering.
About Diligent Robotics
At Diligent Robotics, we are committed to innovating the future of robotics. Our team is dedicated to developing intelligent robots that assist and collaborate with humans in various service roles, transforming industries and enhancing everyday lives.
