Senior UMF Machine Learning Algorithm Engineer
XPENG · Santa Clara, CA
$174,720–$295,680from the description
Jul 21, 2026
Santa Clara, CA
Jul 23, 2026
What this job asks for AI summary
This role centers on building the Lane Fusion system for an autonomous driving platform — fusing lane lines, road boundaries, and other static road elements from multiple perception sources and across time into accurate, stable 3D road representations. The work involves developing computer vision and machine learning algorithms that handle real-world challenges like occlusions, fragmented lanes, and complex road geometry, all within a low-latency, safety-critical vehicle environment. It suits candidates with a strong background in 3D geometry, photogrammetry, or related perception disciplines and solid C++ development skills.
Senior level · 5+ years · Master's required · Full-time
“or” means any one of them counts — you don't need all of them.
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.
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 (4)
Degree requirement: the JD offers two paths — Ph.D. with 3 years of experience, or Master's with 5 years. Master's is the lower formal degree that satisfies the gate, so the degree requirement is set to Masters. The Ph.D. path implies a lower experience floor (3 years), but the Master's path (5 years) is used for the overall years minimum as the more common/accessible route.
The 'hands on experience in one of the following' list (3D reconstruction, noise modeling, lane detection, BEV perception, online mapping) is a pick-one gate from a required section; it is captured as a single preferred-style skill with alternatives, since only one is needed. 'Noise modeling' is omitted from alternatives as it is a generic concept rather than a named tool or technology.
The role sits at the intersection of algorithm/ML research and software engineering (C++ development on a real-time vehicle platform); the alternative occupation code 15-2051 (Data Scientists) reflects the strong ML/algorithm research component.
Ignored 1 non-technology phrase(s) as skills (responsibilities/concepts, not named tools): non-linear optimization.
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.