In this role, you will develop ML-driven perception pipelines for non-traditional sensing modalities, pushing the boundaries of what robots can see, understand, and act upon in challenging real-world environments.

As a Sr. Applied Scientist in Multi-Modal Perception, you will apply deep computer vision expertise alongside classical signal processing techniques for radar and thermal imaging - modalities that provide robustness in adverse conditions and sensing capability beyond the visible spectrum. You will develop ML-based methods to extract semantic and geometric information from radar point clouds, radar tensors, and thermal imagery, and fuse these with camera and depth data to build perception systems that are reliable, comprehensive, and ready for deployment at scale.

Your work will unlock new capabilities for our robots - enabling reliable detection, classification, and scene understanding in low-visibility conditions, cluttered environments, and scenarios where traditional RGB-based perception is insufficient. You will lead research that translates cutting-edge advances in deep learning and computer vision to these underexplored but high-impact sensing modalities.

Join us in building the next generation of multi-modal perception systems that will define the future of autonomous robotics at scale.

Key job responsibilities

- Lead the research, design, and development of ML-based perception pipelines for radar and thermal/infrared imaging modalities

- Develop deep learning models for object detection, classification, segmentation, and tracking using radar data (point clouds, range-Doppler maps, radar tensors) and thermal imagery

- Design and implement multi-modal fusion architectures that combine radar, thermal, camera, and depth data for robust, all-condition perception

- Develop novel representations and feature extraction methods tailored to the unique characteristics of radar and thermal sensors (sparsity, noise profiles, spectral properties)

- Build end-to-end perception systems - from raw sensor data processing and calibration to model training, evaluation, and real-time deployment

- Collaborate closely with Hardware, Navigation, Planning, and Controls teams to define sensor configurations and deliver integrated autonomy solutions

- Establish benchmarks, datasets, and evaluation frameworks for radar and thermal perception

- Mentor scientists and engineers; foster a culture of scientific rigor, innovation, and high-impact delivery

- Publish research findings in top-tier venues (CVPR, ICCV, ECCV, ICRA, NeurIPS, etc.) and contribute to patents

A day in the life

- Train ML models for deployment in simulation and real-world robots, identify and document their limitations post-deployment

- Drive technical discussions within your team and with key stakeholders to develop innovative solutions to address identified limitations

- Actively contribute to brainstorming sessions on adjacent topics, bringing fresh perspectives that help peers grow and succeed - and in doing so, build lasting trust across the team

- Mentor team members while maintaining significant hands-on contribution to technical solutions

About the team

Our team is a diverse group of scientists and engineers passionate about building intelligent machines. We value curiosity, rigor, and a bias for action. We believe in learning from failure and iterating quickly toward solutions that matter.

BASIC QUALIFICATIONS

- Experience programming in Java, C++, Python or related language

- PhD in computer science, electrical engineering, or related field

- 5+ years of hands-on experience in Computer Vision - including object detection, segmentation, tracking, or scene understanding

- Strong expertise in developing and deploying deep learning models for visual perception tasks

- Experience processing and applying ML-based approaches to radar data and/or thermal/infrared imagery

- Strong experience with deep learning frameworks (PyTorch, TensorFlow, or equivalent)

- Proven track record of delivering perception systems from research to production

- Strong publication record in top-tier computer vision, robotics, or ML venues

PREFERRED QUALIFICATIONS

- Experience in the autonomous driving industry, particularly in developing perception pipelines that leverage radar and/or thermal sensors for self-driving vehicles

- Hands-on experience with 4D imaging radar processing, radar signal processing, or radar-camera fusion in AV stacks

- Experience with thermal/LWIR camera systems for pedestrian detection, night-time perception, or adverse-weather sensing conditions

- Familiarity with radar-specific challenges: sparsity, multi-path reflections, clutter, Doppler ambiguity, and cross-modal calibration

- Experience with foundation models or large pre-trained representations adapted to non-RGB modalities (radar, thermal, SAR)

- Knowledge of sensor calibration, synchronization, and extrinsic/intrinsic parameter estimation across heterogeneous sensor suites

- Experience with sim-to-real transfer and synthetic data generation for radar and thermal modalities

- Familiarity with relevant datasets (nuScenes, Radiate, FLIR ADAS, DENSE, Astyx, RADDet, Boreas)

- Experience with real-time inference, model optimization (TensorRT, ONNX), and edge deployment

- Experience with ROS/ROS2 and real-time robotics middleware

The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, and parental leave. Learn more about our benefits at https://amazon.jobs/en/benefits.

USA, CA, SAN FRANCISCO - 192,200.00 - 260,000.00 USD annually