Software Engineer – Map Fusion & Planning
DiDi Labs · San Jose, CA
$141,463–$282,264from the description
Jul 10, 2026
San Jose, CA
Jul 21, 2026
What this job asks for AI summary
This role focuses on building map fusion and motion planning software for autonomous vehicles, sitting at the intersection of HD mapping, real-time sensor perception, and trajectory generation. Day-to-day work spans designing data pipelines and APIs, implementing deep learning-based online mapping networks, developing path and trajectory planning algorithms, and owning the full deployment pipeline from Python training through optimized C++ runtime. It suits engineers with a strong background in robotics, autonomous driving, or spatial computing.
Mid level · 3+ years · National · Bachelor's required · Full-time
“or” means any one of them counts — you don't need all of them.
Posted 3 times — it's one opening, so apply once.
We read this from the posting text with AI. Skim the description below before ruling yourself out.
How this req sits in the market our data
Rare in this occupation — lead with these, and say what you built with them.
Most people in this occupation already list these. Still required — just not what gets you shortlisted.
What the occupation pays Median $138,970 (middle half $107,524–$175,762). This posting is about at that midpoint.
Estimated from BLS employment for this occupation and area, per-skill prevalence across our listing corpus, and published wage benchmarks — as of Jul 28, 2026. It is a model, not a headcount.
Why we read it this way (8)
The posting covers two levels simultaneously — Software Engineer (3+ years, $141,463–$235,182/yr) and Senior Software Engineer (5+ years, $169,783–$282,264/yr). The advertised title is presented as a combined 'Software Engineer / Senior Software Engineer', so the title states no level; the minimum experience gate of 3 years supports a Mid seniority classification for the lower bound of the role.
The compensation range shown ($141,463–$282,264) spans both levels; the true per-level ranges are $141,463–$235,182 (SE) and $169,783–$282,264 (Sr. SE).
No specific work location is stated in the posting beyond a California privacy notice reference, which suggests a US-based role (likely California given DiDi Autonomous Driving's known US operations), but no city or metro is explicitly named.
Degree requirement: the JD lists 'B.S./M.S. or Ph.D.' as a hard qualification with no 'or equivalent experience' escape — minimum is a Bachelor's degree.
DETR-style/query-based BEV perception is listed under required qualifications as a core implementation responsibility, so it is treated as a hard gate even though it names a model architecture rather than a specific library.
ROS2 and DDS appear together as an 'e.g.' example under the required System Design qualification; they are treated as interchangeable middleware options satisfying that hard gate.
ONNX is explicitly called out in the required qualifications ('Python-based training and ONNX optimization') as part of the owned deployment pipeline, making it a hard gate.
All Preferred Qualifications items (MPC/optimization solvers, HD map formats, MapTR/VectorNet, TensorRT, RTOS/safety-critical systems) are listed under a clearly labeled 'Preferred Qualifications' section.
Read the full posting
The employer publishes the full description on their own site — read it there ↗. Or sign in to read it here — it's free, and it also lets you track this application.