Engineer Manager - Perception, Self-Driving Systems

Applied Intuition•Sunnyvale, CA

10d•$231,900 - $298,100•Onsite

About The Position

Applied Intuition is seeking a Technical Lead Manager to oversee the perception model, which is central to their autonomy stack. This role involves managing a single, shared model that serves all Self-Driving Systems (SDS) programs across various vehicle types and environments. The successful candidate will lead the team responsible for training, evaluating, and deploying this model, while also actively participating in architectural and training decisions to enhance its performance. The position requires a hands-on approach to data analysis, evaluation dashboards, and failure analysis, ensuring the model performs effectively across diverse geographies, road types, sensor configurations, and environmental conditions without the need for vertical-specific forks. A key aspect of the role is driving a camera-first perception strategy to minimize reliance on HD maps and lidar. The manager will also oversee the model lifecycle, from training to quantization and deployment on embedded hardware, including device-specific optimizations. Collaboration with OEM customers to understand their sensor configurations, target operational design domains (ODDs), and performance requirements is crucial for translating these into model architecture and data strategies. Additionally, the role involves recruiting, developing, and technically leading a team of perception engineers, fostering a culture of rigorous experimentation and measurement.

Requirements

5+ years in ML/deep learning for perception or 3D scene understanding.
Deep hands-on experience training and deploying vision models at scale.
2+ years managing a perception team, with ability to both set direction and contribute to architecture and training decisions directly.
Experience building production perception systems, especially camera-only or camera-first solutions.
Track record deploying perception models to embedded hardware under real-time latency and compute constraints, including device-specific optimizations.
Strong software engineering in Python and C++, comfortable across the stack from training code to onboard inference integration.
Experience scaling perception models across multiple geographies, sensor setups, or vehicle platforms.

Nice To Haves

Deep familiarity with transformer-based architectures for 3D perception, BEV representations, multi-task learning, and dense prediction.
Familiarity with occupancy-based scene representations, sparse query-based architectures, or temporal aggregation approaches.
Experience reducing or removing map dependencies in perception systems.
Background in autolabel pipelines, data quality monitoring, or data flywheel design for perception.
Experience with closed-loop simulation for perception model evaluation (neural sim, log sim, scenario-based testing).
Experience at an AV company that has shipped perception to production.

Responsibilities

Own the perception model end-to-end: architecture, training, evaluation, and deployment.
Drive a camera-first perception strategy, progressively reducing dependencies on HD maps and lidar.
Lead training and iteration cycles hands-on, including data analysis, evaluation dashboards, and failure analysis.
Own model performance across the full deployment surface, including highway, urban, residential, ramps, complex intersections, poor weather, and hilly terrain, focusing on on-vehicle driving outcomes.
Manage the model lifecycle from training through quantization and deployment on embedded compute, including device-specific optimizations.
Work directly with OEM customer programs to understand sensor configurations, target ODDs, and performance requirements, translating these into model architecture and data strategy.
Recruit, develop, and technically lead a team of perception engineers, setting high technical standards and creating a culture of rigorous experimentation and measurement.