Senior ML Engineer: Agentic AI for Autonomous Driving

Didi Labs; San Jose (CA); On-site; USD 170,000 - 282,000; Full time

Job summary

DiDi Autonomous Driving is seeking a Senior ML Engineer in the United States to work on agentic systems that improve driving software. You will design and evaluate RL and LLM-driven loops, curate a growing skill library, and help produce production-ready policies and data pipelines.

Responsibilities include building agentic harnesses, RSI loops, and tuning models with data. Collaboration with onboard teams will shape architecture for real-world deployment.

Qualifications

• Strong background in machine learning, including deep learning, RL, or decision-making systems.
• Hands-on experience building LLM agent systems with tool use and multi-agent orchestration.
• Experience training or fine-tuning LLMs for agentic workflows, including data curation and RL from feedback.
• Strong Python skills and working C++.
• Rigorous experimental habits and clear measurement/logging.
• Ability to own a system from research prototype to production.

Responsibilities

• Build agentic harnesses for autonomous driving with permissioned access to data, training infra, and evaluation environments.
• Develop RSI loops including failure mining, candidate generation, evolutionary search, and data generation.
• Curate a reusable skill library with verified fixes for reuse in future tasks.
• Train LLMs on agent data and fine-tune to work with our software stack and codebase.
• Advance agent-as-policy approaches by improving driving policy with data and objectives.
• Shape onboard architecture to balance on-vehicle and offline components within latency and safety constraints.
• Collaborate with prediction, planning, simulation, and onboard teams to turn prototypes into production workflows.

Skills

Deep learning

LLM agent systems

Python

C++

Experimentation

Production-ready systems

Education

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

Job description

DiDi Autonomous Driving is seeking a Senior ML Engineer in the United States to work on agentic systems that improve driving software. You will design and evaluate RL and LLM-driven loops, curate a growing skill library, and help produce production-ready policies and data pipelines.

Responsibilities include building agentic harnesses, RSI loops, and tuning models with data. Collaboration with onboard teams will shape architecture for real-world deployment.