Senior ML Engineer, 4D Engine

Avala; San Francisco (CA); Hybrid; USD 150,000 - 210,000; Full time

Benefits offered by this job

Competitive salary

Equity

Comprehensive health/dental/vision

FSA

Unlimited PTO

Job summary

Avala is seeking an experienced ML engineer to own the auto-labeling pipeline, from 3D segmentation to 4D temporal tracking. You will ship models that reduce human effort in creating ground truth for Physical AI and push accuracy improvements toward 95%+.

Based in San Francisco, you will work on cutting-edge 3D vision, point clouds, and multi-sensor fusion, with a team that builds next-generation autonomous systems.

Qualifications

• 5+ years of production ML experience, including 2+ years in 3D perception or autonomous vehicle stacks.
• Strong experience with PyTorch and production model serving (SageMaker or TorchServe).
• Deep understanding of 3D computer vision: point cloud segmentation, object detection, and multi-sensor fusion.

Responsibilities

• Lead the ML models powering Avala's auto-labeling pipeline, from 3D segmentation to 4D temporal tracking.
• Deliver models that achieve high accuracy to reduce human labelling effort for physical AI ground truth data.

Skills

Production ML experience

3D perception

Point cloud processing

Autonomous vehicle perception

PyTorch

Temporal models

Tools

SageMaker

TorchServe

Job description

Posted 6 months ago San Francisco, CA full-time

About This Role

Own the ML models that power Avala's auto-labeling pipeline — from point cloud segmentation to 4D temporal tracking. You'll ship models that run at 89% accuracy today and push toward 95%+, directly reducing the human effort required to create ground truth data for Physical AI.

Requirements

• 5+ years of production ML experience, with at least 2 years in 3D perception, point cloud processing, or autonomous vehicle perception stacks
• Strong experience with PyTorch and production model serving (SageMaker, TorchServe, or equivalent)
• Deep understanding of 3D computer vision: point cloud segmentation, object detection, multi-sensor fusion
• Experience with temporal models (tracking, prediction) is highly valued
• Published research or shipped production systems in 3D perception

Computer Vision 3D Graphics Python PyTorch Machine Learning Point Clouds

What We Offer

Competitive salary and meaningful equity in the team building Fleet Learning Infrastructure for Physical AI

Full health, dental, and vision coverage, plus FSA and unlimited PTO

Work on the closed-loop data infrastructure that the next generation of autonomous systems learns from

A team that built Tesla Autopilot's data infrastructure, now building something bigger