Perception Engineer

Summary

OKSI develops mission-driven defense and sensing technologies for space and security applications. The Perception Engineer will architect and implement perception, detection, tracking, and pose estimation algorithms across EO/IR, multi-spectral, and other sensing modalities, taking models from dataset development through embedded deployment, testing, and flight software integration.

Responsibilities

• Drive the architecture for image processing, object detection, tracking, and pose estimation pipelines for next-generation spacecraft and sensing platforms
• Design and implement robust perception, detection, segmentation, and tracking algorithms (CNN/Transformer-based, e.g., Retina/FCOS/DETR/Mask2D/video models) in C++ and Python
• Build and refine model architectures for EO/IR and multi-spectral imagery, driving foundation-scale datasets, training recipes, and robust generalization to long-tail and degraded conditions
• Train and fine-tune models in PyTorch, with rigorous experiment tracking and reproducible training pipelines
• Build large, diverse datasets and labeling/QA pipelines, including augmentation strategies
• Stand up training and evaluation pipelines (PR/ROC, mAP, latency, robustness suites), with continuous regression testing and model-update loops from field data
• Perform statistical analysis to support algorithm characterization and verification
• Optimize models for real-time embedded inference (quantization/pruning, TensorRT/ONNX Runtime), profiling CPU/GPU performance to meet tight throughput and latency targets on embedded (e.g., Jetson-class) hardware
• Apply model compression techniques (INT8/FP16) and dive into CUDA backends for performance optimization and debugging
• Combine vision outputs with auxiliary sensing (radar/LiDAR/RF) for confirm/deny, association, and track management using decision-level fusion
• Test and verify algorithms via software-in-the-loop (SIL) and hardware-in-the-loop (HIL) simulation, using high-fidelity sensor models and real-world datasets
• Create visualization, triage, and root-cause analysis tools for rapid insight from simulation, HIL, and flight logs
• Define end-to-end test plans in coordination with hardware and flight teams
• Instrument health metrics, drift detection, and graceful degradation logic; write clear tests and documentation mapped to performance requirements
• Work with the software team to integrate algorithms into flight software

Skills

• • Bachelor's degree in Computer Science, Robotics, Electrical Engineering, or a similar discipline (or equivalent experience)
• • 2+ years of experience implementing perception and tracking algorithms deployed in real-world systems
• • Strong production-level C/C++ on Linux and Python for ML and tooling, with a rigorous approach to profiling, optimization, and testing
• • Experience with modern detection/segmentation/tracking model architectures and training/fine-tuning in PyTorch
• • Demonstrated ability to work in a multidisciplinary team and solve complex problems using first-principles approaches
• • EO/IR imagery experience and experience working with real flight or test data in challenging environments
• • Passion for advancing capabilities related to space domain awareness, space security, and/or mission-critical sensing systems
• To conform to U.S. Government export regulations, applicant must be a (i) U.S. citizen or national, (ii) U.S. lawful, permanent resident (aka green card holder), (iii) Refugee under 8 U.S.C. 1157, or (iv) Asylee under 8 U.S.C. 1158, or be eligible to obtain the required authorizations from the U.S. Department of State
• • extensive experience (7+ years) with a track record of shipping ML models to production preferred for senior-level roles
• • Master's or PhD in Computer Science, Robotics, or a similar discipline
• • Deep technical expertise in one or more of: SLAM, nonlinear filtering, image processing, object detection, computer vision, or pose estimation
• • Multi-modal perception experience (EO/IR combined with radar/LiDAR/RF) at the feature or decision level
• • Experience with robustness and safety testing: adversarial/rare-event testing, long-horizon reliability metrics, and dataset shift/drift monitoring
• • Physics-aware imaging experience: radiometric correction, NUC/FFC, atmospheric effects modeling, and synthetic data/simulation for coverage
• • Familiarity with MLOps and data infrastructure: SQL/Parquet, dataset/versioning tools, CI-based validation, and scalable multi-GPU training
• • Strong analytical and problem-solving skills, with the ability to evaluate complex system performance and propose effective solutions
• • Excellent verbal and written communication and cross-functional collaboration skills
• • Self-motivated, with the ability to work independently and within a team-oriented environment
• • Strong initiative, ownership of work products, and commitment to continuous improvement
• • Attention to detail and strong organizational skills, with the ability to manage multiple priorities and meet deadlines

Qualifications

Must Haves

• • Bachelor's degree in Computer Science, Robotics, Electrical Engineering, or a similar discipline (or equivalent experience)
• • 2+ years of experience implementing perception and tracking algorithms deployed in real-world systems
• • Strong production-level C/C++ on Linux and Python for ML and tooling, with a rigorous approach to profiling, optimization, and testing
• • Experience with modern detection/segmentation/tracking model architectures and training/fine-tuning in PyTorch
• • Demonstrated ability to work in a multidisciplinary team and solve complex problems using first-principles approaches
• • EO/IR imagery experience and experience working with real flight or test data in challenging environments
• • Passion for advancing capabilities related to space domain awareness, space security, and/or mission-critical sensing systems
• To conform to U.S. Government export regulations, applicant must be a (i) U.S. citizen or national, (ii) U.S. lawful, permanent resident (aka green card holder), (iii) Refugee under 8 U.S.C. 1157, or (iv) Asylee under 8 U.S.C. 1158, or be eligible to obtain the required authorizations from the U.S. Department of State

Nice to Haves

• • extensive experience (7+ years) with a track record of shipping ML models to production preferred for senior-level roles
• • Master's or PhD in Computer Science, Robotics, or a similar discipline
• • Deep technical expertise in one or more of: SLAM, nonlinear filtering, image processing, object detection, computer vision, or pose estimation
• • Multi-modal perception experience (EO/IR combined with radar/LiDAR/RF) at the feature or decision level
• • Experience with robustness and safety testing: adversarial/rare-event testing, long-horizon reliability metrics, and dataset shift/drift monitoring
• • Physics-aware imaging experience: radiometric correction, NUC/FFC, atmospheric effects modeling, and synthetic data/simulation for coverage
• • Familiarity with MLOps and data infrastructure: SQL/Parquet, dataset/versioning tools, CI-based validation, and scalable multi-GPU training
• • Strong analytical and problem-solving skills, with the ability to evaluate complex system performance and propose effective solutions
• • Excellent verbal and written communication and cross-functional collaboration skills
• • Self-motivated, with the ability to work independently and within a team-oriented environment
• • Strong initiative, ownership of work products, and commitment to continuous improvement
• • Attention to detail and strong organizational skills, with the ability to manage multiple priorities and meet deadlines

Benefits

• Medical, dental, vision fully paid by the employer for the employee
• Three weeks vacation
• Automatic company contribution to 401K – 5% of earned wages (no matching required)
• Educational assistance
• Hybrid schedule options
• Faster-than-typical opportunities to advance your career