Back to Job Listings

Senior/Staff Machine Learning Engineer, Perception

San Francisco

SpringCube

Full-time - Senior Engineer

IT Services & Consulting

Posted 3 weeks ago

$200,000 - $250,000

Contact Employer
  • Share:
Send Feedback
Report This Job

Job Description

This job was selected by the SpringCube team to help AI, Data and Cloud Engineers discover relevant San Francisco Bay Area employers. Sign up to view the full employer details and apply directly with the hiring company.

Company Overview

The company develops physical AI, autonomous machinery, and fleet services for agriculture, turf management, and other industrial applications. Its technology transforms heavy equipment into intelligent autonomous systems designed to operate in demanding environments. By combining machine learning, robotics, and industrial software, the company aims to improve safety, productivity, and operational efficiency while addressing challenges such as labor shortages and environmental sustainability.

Responsibilities

  • Develop real-time perception models for open-world obstacle detection and terrain understanding.
  • Build multimodal sensor-fusion systems that combine camera and LiDAR data into unified 3D and bird’s-eye-view (BEV) representations.
  • Improve perception robustness under challenging conditions, including occlusions, sensor degradation, and GNSS outages.
  • Optimize machine learning models for low-latency inference on resource-constrained embedded hardware while balancing accuracy and computational performance.
  • Design automated labeling pipelines using foundation models and teacher-student distillation techniques to scale data annotation.
  • Develop feedback loops that incorporate real-world field interventions to continuously improve perception models and training data.
  • Build data and evaluation pipelines to curate large-scale multisensor datasets and identify model failures efficiently.
  • Develop visualization and debugging tools that support dataset inspection, performance analysis, and system validation.
  • Analyze perception performance metrics and continuously improve the accuracy and efficiency of different perception subsystems.
  • Develop production-ready software and validate machine learning systems against real-world operational and safety requirements.

Qualifications

  • Master’s or PhD degree in Computer Science, Artificial Intelligence, or a related field, or at least 6 years of industry experience developing vision-based perception systems.
  • Deep expertise in developing and deploying modern perception models, including object detection, segmentation, monocular and stereo depth estimation, metric depth, BEV and occupancy representations, sensor fusion, and 3D scene understanding.
  • Experience adapting, fine-tuning, and distilling large pretrained vision and vision-language models.
  • Strong understanding of multisensor integration involving cameras, LiDAR, and radar, including sensor calibration, spatiotemporal synchronization, and cross-modal fusion.
  • Experience managing large datasets and organizing them for labeling, model training, and evaluation.
  • Strong Python programming skills and experience with PyTorch, TensorFlow, and OpenCV.
  • Ability to develop efficient, production-ready software for real-time systems.
  • Proven ability to design experiments, analyze model performance, and optimize systems using metrics such as mean Average Precision (mAP), Intersection over Union (IoU), inference latency, throughput, and Expected Calibration Error (ECE).
  • Experience optimizing perception systems to meet demanding real-world performance and safety requirements.
  • Ability to work effectively in a fast-moving, collaborative engineering environment with a high level of ownership.

Preferred Qualifications

  • Experience architecting multisensor machine learning systems from the ground up.
  • Experience building large-scale automated labeling pipelines and data-engine feedback systems.
  • Experience optimizing machine learning models for compute-constrained environments, including TensorRT, model quantization, and custom CUDA operations.
  • Familiarity with predictive world models for anticipation, anomaly detection, or closed-loop simulation.
  • Knowledge of emerging policy approaches, including Vision-Language-Action (VLA) and World-Action Models (WAM).
  • Publications at leading computer vision, robotics, or machine learning conferences, such as CVPR, ICRA, CoRL, or RSS.
  • Strong interest in applying AI, robotics, and autonomous systems to industries involving food production, infrastructure, transportation, and industrial operations.

Disclaimer

SpringCube curates tech job listings from various company websites to support tech professionals globally.

  1. No Endorsement: Job ads on SpringCube do not imply endorsement of their authenticity or quality.
  2. No Client Relationship: This company is not a client of SpringCube unless stated.
  3. To Apply: Click the “Apply” button to be redirected to the hiring company’s application page for this job.
  4. No Liability: SpringCube is not liable for inaccuracies.
‹