EdgeTrace unifies your entire camera network into a single, powerful intelligence platform–helping public safety teams detect threats faster, respond in real time, and protect the community.

Founded by engineers from Cruise and xAI, we're a Y Combinator-backed team building AI that works in the chaos of real-world public safety operations. We move fast, value impact over process, and measure our success by the crimes our technology helps solve.

If you want to build mission-critical technology that directly protects communities, let's talk.

About EdgeTrace

YC W24 startup building AI-powered video management systems for law enforcement Real-Time Crime Centers and transportation departments. We help agencies search camera networks in natural language and detect and respond to threats in real time.

Tech Stack

Frontend: Next.js, React, TypeScript, gRPC-Web

Backend: Nest.js, REST, Protocol Buffers, gRPC

AI/ML: Python, PyTorch, TensorRT

GPU: Custom CUDA kernels for video decoding and multi-stream inference

Infrastructure: RabbitMQ, Bazel, Docker, Systemd

Data: Vector database, PostgreSQL-17

Video: ONVIF, RTSP, HLS, WebRTC

What You'll Build

• Vantage VMS features: natural language video search, multi-camera playback, incident reporting
• Vehicle detection and tracking pipelines for DOT traffic analysis
• Real-time alert systems for suspect/vehicle identification
• ONVIF camera discovery and integration services
• Analytics dashboards showing detection accuracy, system health, and search performance

Example Projects

• Multi-camera grid view with synchronized timeline playback
• CJIS-compliant audit logging: track all user actions, video exports, and system access
• Camera auto-discovery via ONVIF with health monitoring and alerting
• Video export with chain of custody: watermarking, MD5 hashing, evidence lock
• Storage management system with retention policies and auto-overwrite
• Role-based access control (Admin/Operator/Viewer) with session management
• Recording scheduler: continuous, motion-based, or time-based per camera
• Bookmarking and evidence tagging for investigation workflows

Requirements

• Pursuing BS/MS in CS or related field
• Experience with React and TypeScript
• Backend experience with Node.js or Python
• Understanding of REST APIs and/or RPC
• Strong debugging skills
• 2026 graduates and US citizens prioritized

Nice to Have

• Next.js or similar frameworks
• Protocol Buffers, gRPC, or RPC frameworks
• Message queues (RabbitMQ, Kafka, Redis)
• Video codecs or streaming protocols
• Docker/containers
• C++ or systems programming
• Interest in computer vision or public safety technology

Details

Duration: 10 weeks (Winter 2026)

Location: On-site in San Mateo (hybrid flexible)

Compensation: $30-40 / hr based on experience

Impact

Your code will help find missing persons, track stolen vehicles, and manage traffic flow. Work directly with YC founders, ship to production systems, and potential for full-time conversion.

Frontend/Backend: TypeScript everywhere with Next.js + NestJS, because type safety matters when bugs could mean missing suspects AI Pipeline: Python for rapid model development, C++ (Userver framework) for production inference where every millisecond counts GPU Optimization: Custom CUDA kernels and TensorRT optimization to search thousands of video streams simultaneously Message Architecture: RabbitMQ orchestrating distributed video processing across GPU clusters

The Technical Challenges: Building computer vision models that work on grainy night footage, rain-covered lenses, and 20-year-old cameras Maintaining sub-second search latency across petabytes of video data Creating legally-defensible audit trails for every search and detection Designing systems that never go down - because crime doesn't stop for deployments