Software Engineer – Map Fusion & Planning

DiDi Labs•San Jose, CA

2h•$129,189 - $214,776

About The Position

DiDi's autonomous driving unit was established in 2016 with the mission of developing Level 4 autonomous driving (AD) technology to make transportation safer and more efficient. In August 2019, the unit became an independent company, DiDi Autonomous Driving, dedicated to advanced AD R&D, product application, and business expansion. We believe integrating AD technology into a shared-mobility fleet will generate immense social value. By leveraging DiDi's specialized technology, operational expertise, and integrated ecosystem, we are positioned to build and operate a highly efficient, user-oriented autonomous fleet. We are seeking a Software Engineer / Senior Software Engineer to develop the next-generation map fusion and motion planning systems for our autonomous vehicles. In this role, you will bridge the gap between semantic HD maps, real-time sensor perception, and vehicle trajectory generation. You will design scalable software infrastructure, implement advanced geometric and deep learning frameworks, and develop the planning algorithms that enable our vehicles to navigate complex, dynamic environments safely and predictably.

Requirements

Education: B.S./M.S. or Ph.D. in Computer Science, Robotics, Electrical Engineering, or a related field.
Experience: 3+ years (Software Engineer) / 5+ years (Senior Software Engineer) of experience in autonomous driving, robotics architecture, or spatial computing.
Software Mastery: Expert proficiency in production-grade C++ (Modern C++14/17/20, multi-threading, memory management) and strong prototyping proficiency in Python.
Motion Planning Fundamentals: Robust foundational knowledge in path planning (e.g., A, Dijkstra, Hybrid A, sampling-based planners like RRT) and kinematic/dynamic vehicle models.
Robotics Core: Deep understanding of robotics fundamentals, including coordinate transformations, spatial geometry, and state estimation.
System Design: Strong system design skills with a solid understanding of middleware (e.g., ROS2, DDS) and distributed software architectures.

Nice To Haves

Trajectory Optimization: Hands-on experience with numerical trajectory optimization methods (e.g., MPC, QP/Nonlinear optimization, interior-point methods) and optimization solvers (e.g., OSQP, Ipopt, Ceres Solver).
Advanced Mapping Experience: Hands-on experience working with HD map formats (Lanelet2, OpenDRIVE) and modern end-to-end learning frameworks (e.g., MapTR, VectorNet) that leverage query-based BEV perception.
Deep Learning Runtime & Deployment: Proven track record of exporting complex deep learning architectures via ONNX and deploying them into real-time C++ production environments using TensorRT.
Anomaly Detection: Proven track record of developing algorithms for map anomaly detection, sensor-to-map misalignments, or online scene-change identification.
Safety-Critical Systems: Knowledge of real-time operating systems (RTOS), deterministic software execution, and safety-critical software design principles.

Responsibilities

System Architecture: Architect the data flow pipelines and APIs for map fusion, real-time map vectorization, and behavior/motion planning modules.
Algorithm Deployment: Design and deploy robust software frameworks that integrate offline High-Definition (HD) maps with online perception data to create a unified local environment model.
Advanced Mapping Networks: Implement and optimize state-of-the-art networks utilizing DETR-style, query-based vector decoding in bird's-eye-view (BEV) for online map element generation.
Motion Planning & Optimization: Design, implement, and validate core motion planning algorithms, establishing a tight feedback loop between vectorized map features, path generation, and trajectory optimization.
Model Deployment Pipelines: Own the end-to-end deployment pipeline for deep learning mapping models—from Python-based training and ONNX optimization to highly efficient runtime execution in C++.
Safety & Anomaly Detection: Develop real-time map anomaly and scene-change detection algorithms to ensure planning system reliability under varying or outdated map conditions.
Performance Optimization: Optimize system latency, CPU/GPU memory footprint, and multi-threaded execution of safety-critical C++ modules.