About the job
Amazon is seeking an exceptional Sr. Applied Scientist to lead the development of perception systems that harness the power of radar and thermal imaging — enabling robots to perceive and operate reliably in conditions where conventional vision alone falls short. 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.
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
Qualifications
Minimum
- 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
- 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