Lead AI Inference & Optimization Engineer (Vehicle & Edge)

didi; San Jose (CA); On-site; USD 170,000 - 351,000; Full time

Job summary

DiDi seeks a Senior/Sr. Staff AI Infrastructure Engineer, Inference & Optimization to lead performance tuning, deployment, and resource scheduling of vehicle-side and cloud AI models.

You will design efficient inference pipelines and tooling to ensure ultra-low latency in autonomous driving, while collaborating with perception/prediction, cloud infra, and safety teams. Ideal candidates have 3–8+ years in AI infrastructure, strong C++/Python, CUDA, and experience with TensorRT/ONNX Runtime;

Qualifications

• Master's degree or higher in CS, software or systems engineering or related field.
• 3–8+ years in high-performance computing, AI infrastructure, model optimization, or embedded deployment.
• Strong proficiency in C++ and Python, with CUDA/OpenMP and low-level profiling tools.
• Experience with TensorRT, ONNX Runtime and LLM inference frameworks (e.g., vLLM, TensorRT-LLM).
• Familiarity with NVIDIA Hopper/Thor architectures and memory bandwidth management.
• Ability to diagnose complex software-hardware integration issues and deliver production-grade solutions.

Responsibilities

• Own deployment, optimization, and resource scheduling of vehicle-side AI models within embedded constraints.
• Lead vehicle-side system stability initiatives and drive resolution for performance bottlenecks.
• Architect and scale service-oriented deployment environments for LLMs and foundational models.
• Track and evaluate industry methodologies, integrating optimization toolchains and quantization.
• Establish profiling and telemetry with CUDA tools to maximize GPU utilization across architectures.
• Collaborate cross-functionally with Autonomous Driving Perception/Prediction, Cloud Infrastructure, and Safety teams to enable rapid algorithm iteration and scalable deployment.

Skills

C++

Python

CUDA

OpenMP

Performance tuning

Cross-functional

Education

Master's or higher in CS/Software/Systems Eng

Tools

TensorRT

ONNX Runtime

vLLM

SGLang

TensorRT-LLM

Job description

DiDi seeks a Senior/Sr. Staff AI Infrastructure Engineer, Inference & Optimization to lead performance tuning, deployment, and resource scheduling of vehicle-side and cloud AI models.

You will design efficient inference pipelines and tooling to ensure ultra-low latency in autonomous driving, while collaborating with perception/prediction, cloud infra, and safety teams. Ideal candidates have 3–8+ years in AI infrastructure, strong C++/Python, CUDA, and experience with TensorRT/ONNX Runtime;