Leads the team this role joins
In-house, owns the opening
Director or head of the group
From your own Gmail and LinkedIn.
About the role
This is a full-time, remote mid-level ML engineering role at Diligent Robotics, based in the USA, for an engineer with at least three years of experience in ML for robotic manipulation. The work is building learning-based manipulation systems that let service robots interact reliably with objects in busy human environments. Responsibilities span models, training data, evaluation tooling, simulation and deployment onto robot hardware. The role works alongside the AI platform team to connect policies with control and safety systems.
What you’ll do
- Develop learning-based models for sensor-driven manipulation, such as reaching and motion generation.
- Build and maintain training pipelines covering dataset creation from robot logs and teleoperation, action representations, augmentation and distributed training.
- Design evaluation metrics and regression tests for manipulation reliability, recovery behavior and safety.
- Build sim-to-real workflows, including simulation environments, domain randomization and failure-mode testing.
- Optimize and distill models for edge hardware and benchmark latency, memory use and stability on target devices.
- Work with the AI platform team to integrate policies with control and safety systems and validate them on robots.
- Analyze field performance, identify dominant failure modes and retrain models using newly collected data.
What they’re looking for
- A bachelor's or master's degree in robotics, computer science, electrical engineering or a related field.
- At least three years applying ML to robotic manipulation, visuomotor control or sequence-to-sequence models.
- Strong PyTorch skills and experience building reliable training and evaluation pipelines.
- Strong Python software engineering skills and the ability to work across ML and robotics teams.
Nice to have
- A PhD.
- Experience with vision-language-action models, behavior cloning, or transformer and diffusion policies for robot control.
- Sim-to-real training experience with tools such as Isaac Sim or MuJoCo, including domain randomization and synthetic data.
- Experience deploying ML models to edge hardware using ONNX or TensorRT, with quantization and performance profiling.
- Familiarity with safety-critical robotics integration and designing fallback and recovery behaviors.
What’s on offer
- A remote, full-time working arrangement based in the USA.
Skills
Questions about this role
Is this role remote?
Yes, the role is remote and based in the USA.
How much experience is required?
At least three years applying ML to robotic manipulation, visuomotor control or related sequence models.
Is a degree required?
A bachelor's or master's degree in a relevant field is required, and a PhD is a plus.