Engineer Manager - ML Data and Evaluation, Self-Driving Systems

Applied Intuition•Sunnyvale, CA

4d•Onsite

About The Position

Applied Intuition is seeking an Engineering Manager to lead the data and evaluation layer for their end-to-end autonomy models. This role encompasses data enrichment, autolabeling, dataset curation, corpus management, evaluation and metrics infrastructure, and closed-loop systems connecting on-road performance to training. The team is responsible for the pace of model iteration across ADAS, L4 trucking, mining, and off-road applications, using a common pipeline. The manager will be hands-on in technical decisions and closely involved with the models.

Requirements

5+ years building ML or data systems for robotics or production software systems.
2+ years managing or technically leading engineering teams.
Experience with large-scale data pipelines: ingestion, curation, and processing of large-scale multi-modal sensor data.
Experience reasoning about dataset composition, distribution balance, and corpus-level quality, making data decisions that measurably improved model performance.
Strong software engineering in Python; comfort with C++ and distributed systems.

Nice To Haves

Shipped perception, prediction, or planning models to production vehicles.
Experience with state-of-the-art simulation for ML eval (e.g. neural rendering and simulation).
Experience with labeling and auto-labeling pipelines: automated pre-labeling, quality verification, human-in-the-loop workflows.
Experience with RL and reward engineering for autonomous driving or robotics.

Responsibilities

Own data enrichment, including ML pipelines for semantic labels, object annotations, behavior tags, and derived features at petabyte scale across various sensors (cameras, lidar, radar), ensuring quality keeps pace with evolving model requirements.
Build curation and corpus management systems for distribution analysis, targeted mining of long-tail scenarios, embedding-based data selection, and enforcement of scenario diversity and geographic balance.
Own evaluation from offboard metrics to on-road driving quality, defining metrics, benchmarks, and regression tests for model shipment.
Close the sim-to-real gap and build 'eval of eval' tooling to measure and improve the evaluation system itself.
Recruit, develop, and technically lead the team, fostering a culture of rigor on a safety-critical system.