Senior ML Engineer: Agentic Driving & Self-Improvement

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

Job summary

DiDi is seeking a Senior ML Engineer for its autonomous driving AI team in San Jose, CA. You will develop agentic systems and contribute to the onboard software architecture, using ML and LLM techniques to improve policy, data, and evaluation loops.

Join a team that blends machine learning, agent-based planning, and production-grade software, delivering scalable improvements with safety gates and real-world driving data.

Qualifications

• Strong background in machine learning including deep learning, reinforcement learning, or decision-making systems.
• Hands-on experience with LLM agent systems, tool use, multi-agent orchestration, or automated evaluation loops.
• Experience training or fine-tuning LLMs for agentic workflows, including trajectory data curation, supervised fine-tuning, or RL from execution feedback.
• Strong Python skills and working C++.
• Rigorous experimental habits: controlled comparisons, held-out evaluation, and a clear line between what was measured and what was assumed.
• Ability to own a system from research prototype to production.

Responsibilities

• Build agentic harnesses for autonomous driving. Agents get permissioned access to the driving stack, data, training infrastructure, and evaluation environments, with automatic scenario setup and pass/fail checks.
• Develop recursive self-improvement (RSI) loops, including failure mining, candidate generation, evolutionary search, and targeted data generation to improve policy weaknesses.
• Curate a reusable skill library, with verified fixes that become knowledge for future tasks.
• Train LLMs on agent data and fine-tune to work with our software stack, tools, and codebase.
• Advance agent-as-policy approaches by editing policy logic, data, training recipes, and tracing driving failures to causes.
• Shape onboard architecture: decide what runs on the vehicle and what stays offline, within latency, compute, determinism, and safety constraints.
• Collaborate with prediction, planning, simulation, and onboard teams to turn prototypes into production workflows.

Skills

Machine learning

LLM agent systems

Python

C++

Experimental rigor

Production-ready systems

Education

BS/MS/PhD in Computer Science, Machine Learning, Robotics, or related field

Job description

DiDi is seeking a Senior ML Engineer for its autonomous driving AI team in San Jose, CA. You will develop agentic systems and contribute to the onboard software architecture, using ML and LLM techniques to improve policy, data, and evaluation loops.

Join a team that blends machine learning, agent-based planning, and production-grade software, delivering scalable improvements with safety gates and real-world driving data.