Systems and Safety Engineer

Who we are

Gatik, the leader in autonomous middle-mile logistics, is revolutionizing the B2B supply chain with its autonomous transportation-as-a-service (ATaaS) solution and prioritizing safe, consistent deliveries while streamlining freight movement by reducing congestion. The company focuses on short-haul, B2B logistics for Fortune 500 retailers and in 2021 launched the world’s first fully driverless commercial transportation service with Walmart. Gatik's Class 3-7 autonomous trucks are commercially deployed across major markets, including Texas, Arkansas, and Ontario, Canada, driving innovation in freight transportation. 

The company's proprietary Level 4 autonomous technology, Gatik Carrier™, is custom-built to transport freight safely and efficiently between pick-up and drop-off locations on the middle mile. With robust capabilities in both highway and urban environments, Gatik Carrier™ serves as an all-encompassing solution that integrates advanced software and hardware powering the fleet, facilitating effortless integration into customers' logistics operations. 

About the role

Gatik is revolutionizing middle-mile logistics with fully driverless commercial box trucks and tractors operating on fixed B2B routes. As a Senior Systems & Safety Engineer for AI/ML, you will bridge the gap between cutting-edge deep learning algorithms (perception, prediction, planning) and rigorous safety engineering. You will define the functional safety and SOTIF strategies for learned components, establish out-of-distribution (OOD) detection criteria, design runtime AI safety monitors, and construct evidence-backed safety cases for machine learning models running on Level 4 autonomous commercial vehicles.

This role is onsite 5 days a week at our Santa Clara, CA  office!

What you'll do

• SOTIF & ML Safety Architecture: Lead the implementation of ISO 21448 (SOTIF) and UL 4600 frameworks across Gatik's AI/ML pipelines.
• Safety Requirements for Learned Systems: Derive safety requirements and performance boundaries (e.g., false positive/negative limits, edge-case coverage metrics) for neural networks and deep learning models.
• Runtime Verification & AI Monitors: Design and validate deterministic AI safety guardrails, out-of-distribution (OOD) detectors, and runtime monitoring mechanisms that fall back to fail-safe actions upon model degradation or uncertainty.
• Dataset Safety & Bias Assessment: Establish criteria for training and validation dataset completeness, operational design domain (ODD) coverage, class imbalance, and synthetic vs. real data fidelity.
• Failure Modes & Effects Analysis: Conduct systematic HAZOP, STPA, and SOTIF risk analyses specifically targeting deep learning failure modes (e.g., adversarial examples, sensor degradation, lighting/weather edge cases).