Software Engineer II, Perception

What you'll do

• Research, develop, and implement perception models and algorithms for tracking actors, classifying attributes, and combining sensor information.
• Analyze large-scale data and testing results, address failure modes, and deliver robust, production-ready software.
• Collaborate across teams to evolve perception architecture and deploy solutions on the real-time Aurora Driver platform.

What they ask for

• Master’s degree or higher in Computer Science, Robotics, Electrical Engineering, or a related field; alternatively, a bachelor’s degree with 1+ years of relevant industry software engineering experience.
• Proficiency in C++ and Python for clean, scalable, efficient production-quality code.
• Basic knowledge in one or more areas such as deep learning, computer vision, recursive state estimation, structured prediction, or numerical optimization.
• Basic knowledge of 3D object tracking algorithms and experience with PyTorch, Tensorflow, and/or other deep learning frameworks.

Nice to have

• Hands-on experience with VLM, foundational or world models, or CUDA/high-performance GPU programming.
• Experience deploying production-grade CV/ML models in real-time environments or optimizing ML training workflows.

Pay

$126,000 - $201,000 per year (base pay; Pittsburgh, PA)

Tools

C++, Python, PyTorch, Tensorflow, CUDA, Hidden Markov models

AI focus

Research, build, and deploy machine-learning models and systems for autonomous-vehicle perception, object tracking, and attribute classification.