Infrastructure Engineer

Description

AITAN builds a multi-drone control platform used in dynamic, high-risk environments.

Our computer vision and AI algorithms don't run in a notebook or in the cloud. They run on drones, utilizing edge compute of different sizes, processing live sensor data in the field.

We are looking for an Algo Infrastructure Engineer to build the infrastructure that every algorithm in our system runs on: a framework for developing computer vision and AI modules, and the deployment, monitoring and tooling that take them from a researcher's laptop to a drone in the field.

You'll work with a group of talented researchers and developers who will be your users, your partners and your toughest reviewers. This is a hands-on role for an engineer who enjoys building developer-facing platforms and cares about how algorithms behave on real hardware.

What You'll Do

• Design and build the framework our algo developers use to write, test and package CV and AI modules
• Build the runtime that runs these modules on drone-onboard and ground compute, including data flow, scheduling and resource management
• Build an "app store" for algorithms: packaging, versioning, deployment and updates across the fleet
• Build observability for algorithms: performance, latency, resource usage, model health and field logs
• Create tooling for testing, benchmarking and replaying recorded sensor data
• Work closely with algo, software, hardware and field teams to take modules from development to operational use
• Improve the developer experience for the whole algo team

Requirements

• 5+ years of experience as a software engineer in backend, infrastructure, platform or systems roles
• Strong programming skills in Python and C++ (or another systems language)
• Strong Linux experience, including debugging, services, and performance and resource analysis
• Experience with containers (Docker) and CI/CD pipelines
• Experience building tools, frameworks or platforms that other developers use
• Experience with logging, metrics and monitoring systems
• Ability to own projects end to end: design, development, deployment and production support
• Ability to work with algorithm developers and understand how CV and ML code is written and run

Nice to Have

• Experience with CV or ML pipelines in production (model packaging, inference serving, ONNX, TensorRT)
• Experience with NVIDIA Jetson or other edge/embedded platforms, including GPU performance tuning
• Experience with robotics messaging systems
• Experience with video and streaming pipelines
• Experience with OTA updates, fleet management or deploying to remote devices
• Experience with simulation or data replay tooling
• Background in robotics, drones, defense or autonomous systems