Senior Machine Learning Engineer, Perception - Autonomous Driving

Build and productize autonomous driving perception systems for traffic signal understanding with solutions designed to work without reliance on HD maps.

Responsibilities

• Design end-to-end perception and AV stack solutions for traffic signal detections across diverse driving environments, from complex intersections to rural roads and highways
• Conduct applied research and development of deep learning models for traffic signal tasks, including:
  • Traffic light detection
  • Traffic sign recognition
  • Road marking detection
  • Construction object detection
  • Text recognition
  • Other traffic signal-related tasks
• Develop generalizable methods to support diverse ODDs and enable country or region expansion
• Drive data-driven development by partnering with large data collection and labeling teams to prioritize high-value data:
  • Data collection prioritization and planning
  • Labeling prioritization
  • Labeling efficiency optimization
  • Maximize the value of data to improve perception accuracy
• Use data simulation and augmentation to address extreme and rare scenarios
• Productize perception solutions by meeting product requirements for safety, latency, and software robustness

Requirements

• Minimum education and experience:
  • PhD with 4+ years, or
  • MS with 6+ years, or
  • BS (or equivalent experience) with 8+ years in Computer Science, Computer Engineering, or a related technical field
• 2+ years of technical leadership with high technical and organizational complexity is a plus
• Hands-on experience building deep learning models and algorithms to solve complex real-world problems
• Proficiency with deep learning frameworks, such as PyTorch
• Experience with data-driven development and collaboration with data and ground truth teams
• Strong programming skills in Python and/or C++
• Strong communication and teamwork skills in a collaborative, learning-focused environment

Technologies

• PyTorch
• Python
• C++
• Deep learning frameworks
• Transformers
• BEV architectures
• Visual Language Models

Benefits

• Eligible for equity and benefits

Ways to Stand Out

• Proven expertise developing generalizable autonomous driving or robotics perception solutions using deep learning with cameras
• Hands-on experience developing and deploying DNN-based solutions to embedded platforms for real-time applications
• Deep learning expertise supported by technical publications in leading conferences or journals
• Expertise with Visual Language Models, Transformers, BEV architectures, and modern traffic signal perception techniques
• Experience with complex object detection and recognition is a plus

Location: Santa Clara, CA (onsite)

Compensation: USD 184,000 - 356,500 per year