Sr / Staff Machine Learning Engineer, Perception

Rivian
Palo Alto, CA, United States
about 2 months ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
5 years minimum
Working hours
Regular working hours
Job source

Tech stack

Computer Vision Big Data C++ (Programming Language) Information Engineering Software Debugging Distributed Systems Monitoring of Systems Python (Programming Language) Machine Learning Object Detection Tensorflow Robotic Automation Software
+8 more
Sensor Fusion Cloud Platform System Pytorch Deep Learning Information Technology Production Code Machine Learning Operations Data Pipelines

Job description

As a Sr./Staff ML Engineer within Rivian’s Perception Team, you will be a core contributor to the architecture, development, deployment, and optimization of advanced machine learning algorithms driving safety-critical, customer-facing features for Rivian’s autonomous vehicles. With a focus on onboard perception (including areas like object detection, sensor fusion, cabin or driver monitoring, and multi-modal state understanding), you will have full ownership over the lifecycle of key perception projects, collaborating closely with cross-disciplinary teams spanning autonomy, planning, simulation, and ML infrastructure. This role is based in Palo Alto, CA.

  • Independently own the design, development, testing, deployment, and maintenance of perception ML models and supporting software for autonomous vehicle applications- including both onboard and cloud environments.
  • Drive the creation and continuous improvement of production-ready perception models for real-time embedded deployment (object detection, tracking, segmentation, pose estimation, scene understanding, etc.), ensuring robustness, performance, and resilience.
  • Architect and build scalable data pipelines and training infrastructure to support ML model iteration with large, complex multi-modal datasets, including auto-labeling and data augmentation capabilities.
  • Develop tools and processes to evaluate and measure the performance and health of perception and/or cabin-monitoring systems, and ensure integration with downstream autonomy modules.
  • Analyze, debug, and optimize perception system performance, from offline metrics and simulation validation to live, in-vehicle operation, addressing limitations like manual labeling bandwidth, ground truth availability, and real-world heterogeneity.
  • Collaborate tightly with teams across machine learning, sensor systems, embedded platform, planning, infrastructure, and data engineering to deliver integrated, customer-impacting autonomous features.
  • Share technical direction, mentor junior engineers, publish internal guidance, and help shape Rivian’s technical roadmap in perception.
  • Stay abreast of state-of-the-art research in machine learning, computer vision, and autonomous driving; drive adoption of best practices and pioneer new approaches where appropriate

Requirements

  • BS, MS, or PhD in Computer Science, Robotics, Electrical/Mechanical/Aerospace Engineering, or a related technical field.
  • 5+ years of experience (Sr.), or 7+ years (Staff), developing and deploying deep learning models for autonomous vehicles, robotics, or other safety-critical, real-time embedded systems.
  • Expert proficiency with Python and one or more deep learning frameworks (e.g., PyTorch, TensorFlow); strong C++ skills for performance-critical, production code.
  • Demonstrated experience architecting, training, and evaluating perception models (2D or 3D, including sequential models), with exposure to deployment on real vehicles and/or production robotic systems.
  • Track record in building or leveraging complex training infrastructure (cloud and/or cluster-based) and working with large-scale datasets in distributed environments.
  • Hands-on experience with several of the following: Vision foundation models, temporal/spatial modeling, attention/transformer architectures, auto-labeling systems, data augmentation for diverse sensor configurations.
  • Sensor signal decoding (camera, radar, lidar), multi-modal sensor fusion, pose/trajectory estimation, action or intent recognition, and state-of-the-art driver/passenger monitoring.
  • System and algorithmic optimization, robust software engineering best practices, and empirical performance analysis.
  • Highly effective communicator and team collaborator; demonstrated ability to partner across technical specialties and organizational boundaries to deliver end-to-end solutions.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on indeed.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

2:35 min

Preventing remote code execution in PyTorch models

Balázs Kiss · WWC 2023

3:28 min

Defining big data and machine learning fundamentals

Ayon Roy · LIVE

1:39 min

Fundamentals of tensors and the TensorFlow library

Håkan Silfvernagel · LIVE

3:37 min

Transitioning automated driving to neural networks and model-based perception

Katrin Lehmann Katrin Lehmann +1 · WWC 2025

4:41 min

Replacing PyTorch with ONNX runtime for AWS Lambda deployments

Marek Suppa · LIVE

3:55 min

Evaluating central server APIs against edge deployment models

Hauke Brammer · WWC 2021

Videos

See all

Related articles

See all