Staff Deep Learning Engineer, State Estimation (R5785)

Role overview

Join a state estimation and vision team to build deep learning capabilities that allow autonomous platforms to understand their motion and localize when GPS is unavailable or unreliable. The work sits at the intersection of deep learning, 3D computer vision, and geometric estimation, developing learned components for vision-based navigation. The role owns the full model development pipeline, from tool selection and annotation planning through training, evaluation, integration support, and deployment recommendations.

Responsibilities

- Develop and evaluate models for feature detection and matching, visual correspondence, depth estimation, relative pose estimation, and image-to-map localization. - Combine learned visual representations with geometric methods to improve localization accuracy, robustness, and recovery under challenging conditions. - Own data preparation and supervision strategies, including dataset curation, annotation requirements, labeling tools, automated quality checks, and coverage analysis. - Design evaluations that measure both model performance and downstream localization outcomes across changes in lighting, viewpoint, altitude, terrain, weather, and sensor characteristics. - Profile models against onboard compute, memory, and latency constraints, partnering with deployment engineers on optimization and runtime validation. - Deliver tested, documented components and interfaces, collaborating with software, systems, and flight test teams.

Requirements

- M.S. in Aerospace Engineering, Electrical Engineering, Robotics, Computer Science, or a related field, with 4+ years of relevant professional experience (or 2+ years with a Ph.D.). - Hands-on experience designing, training, debugging, and evaluating models using PyTorch or an equivalent framework, including architecture selection, loss design, optimization, and augmentation that preserves geometric consistency. - Strong foundations in camera models, coordinate transformations, projective geometry, and multi-view geometry, with practical experience in at least one area such as visual navigation, visual geolocation, Structure from Motion, SLAM, 3D reconstruction, or depth estimation. - Strong Python skills and a demonstrated ability to take a computer vision capability from problem definition and raw data through training, evaluation, and integration readiness. - Experience building pipelines for sensor data ingestion, cleaning, filtering, deduplication, and dataset versioning, along with reproducible training workflows that include experiment tracking and configuration management.

Nice to have

- Experience with aerial imagery, geospatial data, elevation maps, or matching observations across viewpoint, lighting, season, or sensor modality. - Experience with model export, quantization, TensorRT, ONNX, or deployment on embedded compute platforms. - Experience validating perception or robotics systems on physical platforms. - Familiarity with methods such as correlation or cost volumes, learning priors over scene geometry, or applying diffusion models or flow matching to computer vision. - Background in aerospace or defense.

Benefits and work setup

- Compensation listed at $200,000–$300,000 per year, plus bonus, benefits, and equity for full-time regular employees. - Offers contingent on a cleared background and possible reference check. - Equal opportunity employer committed to inclusive hiring.