Senior Software Engineer (C++), Video Processing

We are a Site Intelligence company transforming how industrial businesses operate. Our platform turns your existing infrastructure into a source of actionable operational intelligence, enabling teams to see what's happening, understand why, and improve continuously. By surfacing the operational signals that reports miss, we help the world's largest logistics, manufacturing, and warehousing operators stay one step ahead, making operations visible and driving proactive safety. We're a fast-growing, high-agency team building category-defining products by leveraging the latest technologies in computer vision and AI.

Industry leaders like DHL, Amazon, and Tesla trust Protex AI to drive measurable safety improvements, achieving an average 64% risk reduction within just three months of deployment. Operating in 20+ countries, Protex is the go-to safety partner for Fortune 500 manufacturing and logistics enterprises, transforming workplace safety with real-time, AI-powered insights.

About the Team

The Computer Vision (CV) Team builds and maintains the core foundation that powers all Protex systems, ensuring robust edge-to-cloud connectivity, scalable data infrastructure, and high-performance backend services. We support edge deployments for real-time computer vision applications and deliver resilient systems to enable proactive workplace safety at global scale.

About the Role

We're looking for a Senior Software Engineer to join our Computer Vision team. You'll own features end to end on a performance-critical, real-time system: from the video analytics pipeline on the edge, through the Python services around it, to the events our clients see in the cloud.

The edge pipeline is built on the NVIDIA DeepStream SDK and GStreamer. It runs on edge hardware and orchestrates decode, batching, inference, tracking, and analytics under latency and throughput constraints. Most of it is modern C++ and CUDA, and the systems around it are Python and AWS.

You'll bring a strong background in performance-critical software and a product mindset. You care about what the client sees, you ship across language and system boundaries when the problem needs it, and you use modern tools, including AI-assisted development, as a normal part of your workflow.

What You'll Do

Design, build, and ship features across the edge pipeline, the Python services around it, and the cloud backend.

Own the performance, reliability, and observability of the systems you build, from custom GStreamer plugins to edge-to-cloud delivery.

Make performance and architecture trade-offs with product context: latency, throughput, and cost against client value.

Investigate and resolve issues on live client systems, using logs, metrics, and device telemetry.

Work closely with the Computer Vision, Product, and Infrastructure teams to turn safety use cases into deployed features.

Review code, mentor engineers, and influence the technical direction of the team.

What You'll Need

5+ years of professional software engineering experience.

A track record of shipping and operating production software, and of owning features across system boundaries.

System design experience, with pragmatic trade offs across technical and product constraints

Strong background in performance-critical software development, preferably in modern C++. Equivalent depth in Rust or C with working C++ knowledge is also welcome.

Experience with real-time or performance-aware systems: profiling, concurrency, and debugging of multi-threaded applications.

Clear written and spoken communication, and the ability to explain trade-offs to engineers and non-engineers.

Ability to influence technical direction, mentor others, and implement solutions.

Working proficiency in Python for services, tooling, and test harnesses.

Experience building and deploying with Docker, including on resource-constrained edge devices.

Daily use of AI-assisted development tools for code, review, and investigation, and a critical eye for their output.

A habit of learning new tools, languages, and domains quickly, and of applying them in production.

Nice to Have

Hands-on experience with the NVIDIA DeepStream SDK

Hands-on experience with GStreamer and computer vision applications, including writing or maintaining custom GStreamer plugins (pads/caps negotiation, buffer/metadata handling)

CUDA and GPU programming experience, including GPU memory management on NVIDIA hardware (Jetson-class edge devices)

Experience deploying ML inference in production (TensorRT, ONNX Runtime, or similar)

Knowledge of encoding/decoding algorithms (H.264, H.265, MJPEG) and streaming protocols

Experience with edge deployment on AWS IoT Greengrass (or similar edge runtimes) and edge-to-cloud IPC

Experience with AWS cloud services and event-driven backends

Experience with CMake-based build systems

A track record of building observability into real-time systems (structured logging, health/heartbeat signals, graceful degradation)

Bachelor's degree in Computer Science or a related field

Why Join Us

At Protex AI, you'll work on cutting-edge problems with a mission-driven team. You'll have ownership, autonomy, and the opportunity to make a tangible impact on workplace safety around the world.

Protex AI is an inclusive and equal opportunities employer. We are committed to creating an equitable workplace for everyone regardless of gender, civil status, family status, sexual orientation, religion, age, disability, education level, or race.