Staff Machine Learning Engineer - Perception
Cssmerge · San Francisco, CA
About this role
**Who we are** Atoms is building the machines that power the next era of progress—real-world robots for industries that move civilization forward (starting with food, mining, and transport). We design systems to understand, predict, and control the physical world with precision, turning complex operations into something more reliable, scalable, and productive. **About the role (Staff/Senior Staff Machine Learning Engineer — Perception)** As a foundational technical leader in Atoms’ AI organization, you’ll help define how our machines transform raw sensor data into rich representations of the physical world. You’ll work across camera, LiDAR, radar, audio, and other sensor modalities to build perception systems that operate in complex, dynamic environments. This is not just improving an existing perception stack—you’ll help determine what the stack should become, collaborating closely with AI research, robotics, autonomy, and engineering leaders. This is a deeply technical individual contributor role with significant influence over Atoms’ technical direction. **What you’ll do** - Define and help build the technical architecture for Atoms’ next-generation perception systems - Develop ML systems that transform multimodal sensor inputs (camera, LiDAR, radar, audio, and more) into useful representations of the physical environment - Advance multi-sensor and multimodal fusion for complex real-world operating environments - Design and develop deep learning architectures for detection, segmentation, tracking, classification, scene understanding, and 3D perception - Explore how foundation models and world models can complement or replace parts of traditional perception pipelines - Build perception systems that serve downstream reasoning, planning, and action models - Make architectural decisions across data, model design, training, evaluation, inference, and deployment - Balance model quality with latency, efficiency, reliability, and compute constraints for real-world machines - Establish evaluation methodologies and metrics that reflect performance in real operating environments - Partner across world models, action models, robotics, autonomy, and ML infrastructure - Provide technical leadership via architecture reviews, mentorship, technical direction, and hands-on engineering - Help set the technical bar for the growing perception organization and help identify exceptional talent **What we’re looking for** - Deep expertise in machine learning and computer vision, with substantial experience building sophisticated perception systems - Strong understanding of modern deep learning architectures for visual and multimodal perception - Experience with one or more real-world sensor modalities (cameras, LiDAR, radar, audio, depth sensors, etc.) - Experience with sensor fusion, multimodal learning, 3D perception, scene understanding, or related areas - Strong grasp of the full ML lifecycle: data strategy, training, architecture, evaluation, optimization, and deployment - Experience designing ML systems under real-world latency, compute, reliability, and safety constraints - Strong software engineering fundamentals; ability to stay hands-on in Python and/or C++ - Proven ability to make consequential technical/architectural decisions in ambiguous problem spaces - Track record of technical leadership and influencing engineering direction beyond your immediate projects - Ability to communicate complex technical ideas clearly and collaborate across res
Listing freshness
CronJobs last confirmed this listing 58m ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.