ML Engineer, Motion Planning

Didi Labs; San Jose (CA); On-site; USD 170,000 - 339,000; Full time

Job summary

DiDi Labs is seeking an experienced Machine Learning Engineer to advance the ML-powered planning system for Voyager's autonomous driving platform. You will leverage frontier ML techniques with access to petabytes of real-world driving data.

You will collaborate with ML Infrastructure, Perception, Prediction, Planning, and Systems teams to deploy robust, scalable models under onboard compute and safety constraints.

Qualifications

• BS, MS, or PhD in Computer Science, Machine Learning, Robotics, Electrical/Mechanical Engineering, or related field, or equivalent practical experience.
• 3+ years in machine learning, autonomous driving, robotics, or related fields (Senior) or 5+ years (Staff).
• Proven track record of developing and deploying ML models in production, ideally for real-time, embedded, or autonomous driving systems.
• Strong proficiency in Python and C++, with production-grade software development.
• Deep understanding of transformers, BEV/3D representations, and trajectory prediction/generation models.
• Foundations in linear algebra, control theory, or motion planning (path/trajectory generation, lane/road geometry).
• Experience applying ML to motion planning, robotics, or related decision-making problems.
• Ability to own ambiguous technical challenges end-to-end, balancing research innovation with production constraints.

Responsibilities

• Develop ML-powered systems that generate driving behavior decisions, scene understanding, and trajectories.
• Frame driving challenges as ML problems; apply imitation learning, RL, learned planners, and end-to-end models.
• Design data-driven algorithms to improve safety, generalization, and reliability of autonomous driving.
• Develop hybrid planning that integrates ML with rule-based and optimization-based planning.
• Evaluate large-scale ML models using real-world data and simulation within onboard constraints.
• Build iteration pipelines, scenario mining, closed-loop simulation, and metrics tied to real-world performance.
• Collaborate with ML Infrastructure, Perception, Prediction, Planning, Mapping, and Systems Engineering teams.

Skills

Python

C++

PyTorch

JAX

TensorFlow

Reinforcement learning

Imitation learning

Trajectory planning

Motion planning

Education

BS/MS/PhD in CS/ML/Robotics or related

Tools

PyTorch

JAX

TensorFlow

CUDA

TensorRT

Job description

Founded in 2016, DiDi's autonomous driving unit is dedicated to developing Level 4 autonomous driving technology to make transportation safer, more efficient, and accessible. In 2019, the unit became an independent company, Voyager, to accelerate technology development, commercialization, and large-scale deployment. By combining DiDi's unique data advantage, operational expertise, and mobility ecosystem, we aim to build a reliable, scalable autonomous fleet that integrates seamlessly with human-driven services. Driven by real-world customer needs and a strong commitment to safety and user experience, our mission is to deliver autonomous mobility solutions that create meaningful value for riders and communities.

About The Role

We are looking for an experienced and driven Machine Learning Engineer to join our autonomous vehicle team and develop the next-generation ML-powered planning system for Voyager's autonomous driving platform. You will leverage frontier ML techniques, including learned planners and end-to-end models, to build intelligent systems that understand complex driving environments, make data-driven decisions, and navigate safely and efficiently. Working alongside leading industry experts, you will leverage DiDi's unique data advantage, including petabytes of real-world driving data, to advance model performance, build robust evaluation frameworks that correlate with on-road safety, and accelerate the deployment and scaling of our driverless technology.

Responsibilities

Develop next-generation ML-powered systems that generate driving behavior decisions, scene understanding, and trajectories to support our L4 autonomous driving deployment roadmap.

Frame open-ended, real-world driving challenges as well-defined ML problems; research and apply cutting-edge techniques, including imitation learning, reinforcement learning, learned planners, and end-to-end models.

Design data-driven algorithms that improve the safety, generalization, and reliability of autonomous driving, including robust scene understanding and planning in complex or changing road environments.

Develop hybrid planning solutions that integrate ML-driven approaches with traditional rule-based and optimization-based planning, leveraging their complementary strengths to achieve superior safety, efficiency, and robustness in complex driving scenarios.

Develop and evaluate large-scale ML models using real-world driving data and simulation, translating learned representations into actionable planning guidance and integrating models into production systems under onboard compute, latency, and safety constraints.

Build infrastructure for rapid iteration, including challenging scenario mining, training and evaluation pipelines, closed-loop simulation, and metrics that correlate with real-world driving performance.

Collaborate closely with ML Infrastructure, Perception, Prediction, Planning, Mapping, and Systems Engineering teams to investigate failures, drive end-to-end improvements, and deploy solutions into real-world autonomous driving.

Qualifications

B.S., M.S., or Ph.D. in Computer Science, Machine Learning, Robotics, Electrical Engineering, Mechanical Engineering, or a related technical field, or equivalent practical experience.

3+ years of industry experience for Senior, or 5+ years for Staff, in machine learning, autonomous driving, robotics, or related fields.

Proven track record of developing and deploying ML models in production, ideally for real-time, embedded, or autonomous driving systems.

Strong proficiency in Python and C++, with experience developing robust, efficient production software and hands‑on experience with modern deep learning frameworks (e.g., PyTorch, JAX, TensorFlow).

Deep understanding of modern deep learning techniques, including transformers, BEV and 3D representations, and trajectory prediction or generation models, with hands‑on experience in model training, evaluation, and debugging.

Foundations in linear algebra, control theory, or motion planning, including path and trajectory generation, trajectory evaluation, cost function design, and lane and road geometry.

Experience applying machine learning to motion planning, robotics, or related decision-making problems, with the ability to integrate learning-based approaches with traditional planning methods.

Demonstrated ability to own ambiguous technical challenges end to end, balancing research innovation with production constraints, safety, reliability, and engineering trade-offs.

Demonstrated technical impact through research publications, open-source contributions, or significant achievements in industry.

Preferred Qualifications

Strong engineering experience applying ML-driven approaches to solve complex real-world problems, with a proven track record of translating research ideas into robust, production-quality systems and successfully deploying them.

Experience integrating learning-based approaches with traditional rule-based or optimization-based planning systems to improve safety, efficiency, and robustness.

Experience with closed-loop simulation, large-scale evaluation, and data-driven model iteration for autonomous driving.

Experience mentoring junior engineers, supervising research interns, or leading small technical teams.

Experience with road-structure representations, including lane graphs, topology reasoning, scene understanding, or uncertainty estimation in complex driving environments.

Experience with end-to-end autonomous driving models, learned planners, vision-language models, or foundation models applied to driving and robotics.

Experience deploying and optimizing ML models for real-time onboard inference, including TensorRT, CUDA, quantization, and compute or latency optimization.

Publications at leading conferences such as CVPR, ICCV, ECCV, NeurIPS, CoRL, ICRA, IROS, or IV, or equivalent demonstrated technical impact in industry.

The annual base salary range for the Senior ML Engineer position is $169,783–$282,264, and for the Staff ML Engineer position is $203,726–$338,694. In addition to base salary, compensation includes bonus, equity, and benefits. Thesalary ranges are determined by role, level, and location. Individual compensation within the range depends on several factors, including work location, job-related skills, relevant experience, and education or training.

I acknowledge that prior to submitting this application, I have read and accepted the Privacy Notice for California Residents which is available on https://v.didi.cn/AQnxlBa