AI Perception Engineer Jobs

View detail

Design, implement, and maintain perception systems for autonomous robots operating in real-world environments, focusing on robust localization and mapping in unstructured, off-road, and field conditions. Develop and integrate perception algorithms that fuse data from multiple sensors such as LiDAR, cameras, RADAR, and inertial sensors, supporting new sensing modalities as robotic platforms evolve. Deploy perception software on physical robots, debugging and resolving issues during on-robot testing and field operations, and collaborate with autonomy, controls, and platform teams to integrate perception into the overall autonomy stack. Improve system robustness and scalability by contributing to code quality, testing, and maintainability, along with developing tools and metrics to monitor performance and detect regressions. Collaborate with engineers, researchers, and operators to define perception requirements, deliver reliable solutions, communicate technical information to stakeholders, and support field operations and customer demonstrations to ensure perception systems are production-ready.

View detail

Execute the PCP metrics pipeline to assess how hardware updates across various sensors affect PCP performance sensitivity in 3D scene understanding, live mapping, and localization, especially under adverse weather and winter conditions. Design and conduct structured A/B testing experiments, including side-by-side custom mount runs and tandem vehicle data collection, to clear sensors for winter ODD. Collaborate with Autonomous Hardware Engineering (AHE) to correlate sensor-specific lab tests with downstream PCP performance. Detect root cause regressions to understand compensation by early fusion models for modality degradation in challenging environments. Design and develop performant and efficient multi-sensor fusion models to leverage advantages of on-board low-cost sensors to improve Perception performance on highways and in adverse weather.

View detail

As a Senior Perception Engineer at Chef Robotics, you will own the full stack of how robots see and understand the world, including integrating camera hardware, training deep learning models, and ensuring real-time model performance on the factory floor. You will design, train, and optimize deep learning models for detection, segmentation, pose estimation, and classification, focusing on real-world robustness. You will build low-latency inference pipelines optimized for embedded and edge hardware, develop multi-object tracking algorithms, and solve perception problems specific to food robotics such as deformable objects and occlusions. You will manage the end-to-end machine learning lifecycle including data collection, annotation tooling, dataset curation, augmentation, model training, evaluation, deployment, and debugging in the field. Additionally, you will develop tooling to monitor model performance in production, partner with robotics, hardware, and software engineers to translate perception capabilities into robot behaviors, help define the perception roadmap, influence the team's technical direction, and assist in integrating new cameras and sensors for enhanced robotic vision.

View detail

Develop a high-throughput rendering pipeline for training robotics foundation models. Design protocols and interfaces between the rendering pipeline, physics engine, and 3D generative models. Build an efficient platform for large-scale robotics training and evaluation. Build a closed-loop system to minimize the sim-to-real gap in rendering for robotics policy training. Collaborate with a team of driven individuals committed to building general-purpose Physical AI.

View detail

Build Vision-Language-Action models for robotics control end-to-end including data curation, careful evaluation, model architecture design, training and inference stacks, and rigorous experiments. Collaborate with simulation and real-world robotics teams to curate high-quality, diverse, and large-scale datasets. Curate Internet-scale datasets for embodied perception and first-person robot video generation. Design new generative simulation techniques to expand simulation data scale and diversity, train and evaluate generative models of 3D objects and environments, and language/code models to generate tasks and reward functions. Collaborate with a team committed to building general-purpose Physical AI.

View detail

As a Staff Software Engineer on the Perception team, you will be responsible for defining and driving the long-term vision and architecture for perception systems, architecting complex, scalable, and robust end-to-end perception and robotics systems for deployment on real-world hardware, ensuring their successful integration into Hayden’s core product platform. You will spearhead the architectural design, implementation, and long-term ownership of next-generation perception systems, transition research prototypes to production solutions, deliver high-performance, tested, and maintainable C++ code optimized for edge and robotics platforms, architect and optimize real-time perception pipelines, drive the integration of state-of-the-art ML and CV models, provide technical leadership in complex problem domains, collaborate with Product leadership and Engineering organizations, and contribute to foundational shared infrastructure, tooling, and architectural patterns to scale pilot initiatives into core product capabilities.

View detail

As a Senior State Estimation Engineer at Hayden AI, the responsibilities include deriving and implementing novel real-time pose estimation algorithms, researching, developing and implementing algorithms to solve large-scale mapping and similar problems, collaborating with other engineers on multi-sensor calibration both in-situ and in-factory, programming and developing software in C++ and/or Python, contributing to high impact multidisciplinary projects across teams, collaborating with deep learning, device, and cloud teams to improve overall system architectures, and providing mentorship to junior engineers.

View detail

Lead the research and development of novel deep learning algorithms that enable robots to perform complex, contact-rich manipulation tasks. Explore the intersection of computer vision and robotic control by designing systems that allow robots to perceive and interact with objects in dynamic environments. Create models that integrate visual data to guide physical manipulation, moving beyond simple grasping to sophisticated handling of diverse items. Collaborate with a multidisciplinary team of engineers and researchers to translate cutting-edge concepts into robust capabilities that can be deployed on physical hardware for industrial applications. Research and develop deep learning architectures for visual perception and sensorimotor control in contact-rich scenarios. Design algorithms that enable robots to manipulate complex or deformable objects with high precision. Collaborate with software engineers to optimize and deploy research prototypes onto physical robotic hardware. Evaluate model performance in simulation and real-world environments to ensure robustness and reliability. Identify opportunities to apply state-of-the-art advancements in computer vision and robot learning to practical industrial problems. Mentor junior researchers and contribute to the technical direction of the manipulation research roadmap.

View detail

Lead multidisciplinary teams in autonomy, integration, and testing by aligning technical efforts, resolving cross-functional challenges, and driving mission-focused execution while balancing hands-on technical oversight with performance optimization, innovation, and stakeholder communication. Design and implement advanced perception algorithms for object detection, classification, and multi-target tracking across diverse sensors. Integrate data from vision systems, radars, and other sensors using probabilistic and deterministic fusion techniques to generate accurate situational awareness. Develop and refine state estimation algorithms for localization and pose estimation using IMU, GPS, vision, and other sensing inputs. Interpret sensor ICDs and technical specifications to ensure proper data handling and synchronization. Optimize perception pipelines for performance, robustness, and real-time efficiency in simulation and real-world environments. Collaborate closely with autonomy, systems, and integration teams to interface perception outputs with planning, behaviors, and decision-making modules. Validate algorithms using synthetic data, simulations, and field testing. Coordinate with hardware and sensor teams to integrate perception algorithms with onboard compute platforms and sensor payloads. Drive innovation in airborne sensing techniques for unmanned aircraft operating in complex or contested environments. Travel approximately 10-15% of the year to office locations, customer sites, and flight integration events.

View detail

Lead the research and development of novel deep learning algorithms that enable robots to perform complex, contact-rich manipulation tasks. Explore the intersection of computer vision and robotic control, designing systems that allow robots to perceive and interact with objects in dynamic environments. Create models that integrate visual data to guide physical manipulation, moving beyond simple grasping to sophisticated handling of diverse items. Collaborate with a multidisciplinary team of engineers and researchers to translate cutting-edge concepts into robust capabilities that can be deployed on physical hardware for industrial applications. Research and develop deep learning architectures for visual perception and sensorimotor control in contact-rich scenarios. Design algorithms that enable robots to manipulate complex or deformable objects with high precision. Collaborate with software engineers to optimize and deploy research prototypes onto physical robotic hardware. Evaluate model performance in both simulation and real-world environments to ensure robustness and reliability. Identify opportunities to apply state-of-the-art advancements in computer vision and robot learning to practical industrial problems. Mentor junior researchers and contribute to the technical direction of the manipulation research roadmap.