Base Salary
$170k - $339k/yr
Responsibilities
- Own deployment, optimization, and resource scheduling for vehicle-side AI models under embedded constraints.
- Lead vehicle-side system stability initiatives, root-cause analysis, and resolution of system-level performance bottlenecks and runtime anomalies.
- Architect and scale service-oriented deployment environments for LLMs and foundation models used in offline simulation, automated annotation, and model validation.
- Evaluate and integrate optimization toolchains, quantization techniques, and execution engines.
- Build profiling and telemetry frameworks with CUDA tools to monitor and improve GPU hardware utilization.
- Collaborate with Autonomous Driving Perception/Prediction, Cloud Infrastructure, and Safety teams to accelerate algorithm iteration and vehicle deployment.
Requirements
- Bachelor’s or higher degree in Computer Science, Software Engineering, Systems Engineering, or a closely related technical field.
- 3–8+ years of industry experience in high-performance computing, AI infrastructure, model optimization, or embedded deployment.
- Strong proficiency in C++ and Python, with expertise in parallel programming using CUDA and OpenMP and low-level system profiling tools.
- Deep familiarity with TensorRT, ONNX Runtime, vLLM, SGLang, and TensorRT-LLM.
- Understanding of modern GPU architectures such as NVIDIA Hopper and Thor and of memory bandwidth management.
- Ability to diagnose complex software-hardware integration issues and deliver scalable, production-grade solutions.
- Preferred experience optimizing and deploying models on NVIDIA Thor, serving foundation models with vLLM, SGLang, TGI, or LightLLM, and using PyTorch, model quantization, kernel fusion, or graph compilation.
- Preferred experience deploying real-time, high-availability AI workloads in autonomous vehicles, robotics, or edge devices.
Benefits
- Bonus, equity, and benefits are provided in addition to base salary.
- Full-time position.
About DiDi
DiDi Global Inc. is a leading mobility technology platform. It offers a wide range of app-based services across Asia Pacific, Latin America, and other global markets, including ride hailing, taxi hailing, designated driving, hitch and other forms of shared mobility as well as certain energy and vehicle services, food delivery, and intra-city freight services. DiDi provides car owners, drivers, and delivery partners with flexible work and income opportunities. It is committed to collaborating with policymakers, the taxi industry, the automobile industry, and the communities to solve the world’s transportation, environmental, and employment challenges through the use of AI technology and localized smart transportation innovations. DiDi strives to create better life experiences and greater social value, by building a safe, inclusive, and sustainable transportation and local services ecosystem for cities of the future.