Systems Engineer

About Rabot

Rabot builds vision AI for warehouse packing operations. Cameras watch the pack line, software figures out where things are slow or wrong, and operators get real-time feedback that actually changes how they work. Customers stick around because it measurably improves their output.

We're venture-backed with distribution partnerships with major industry players. The product works. Now we need engineers to push the real-time systems further.

The role

You'd work on the software that runs on and around our hardware. The real-time pipeline: cameras, on-device AI models, video processing, edge compute, and the systems that tie it all together. This is the layer between the physical world and our AI.

You'll work closely with our hardware engineer on the full perception and processing stack. Latency matters. Reliability matters. These systems run in warehouses, not data centers, and they need to work every time.

3+ years of experience required. We care less about where you worked and more about what you've built and how it performed.

In-person in Arlington, TX. Not remote.

What you'll do

• Build and optimize real-time software systems. Video pipelines, inference engines, edge processing, device communication.

• Write performant code for critical paths and scripting for tooling, orchestration, and model integration.

• Work with the hardware team on the full stack from camera to cloud. You'll understand the hardware constraints and write software that respects them.

• Profile and optimize. Latency budgets, memory constraints, CPU/GPU utilization on edge devices. You measure before you guess.

• Ship reliable software to devices running in warehouses. These aren't dev environments. They need to run for months without intervention.

• Improve deployment, testing, and monitoring for edge systems.
  

Who you are

• You have 3+ years of experience writing software for systems that run in production. Not just scripts. Real systems with real performance requirements.

• You understand real-time constraints. You've worked on software where latency and throughput actually matter, not just on paper.

• You're comfortable close to the hardware. You don't need to design PCBs, but you understand device constraints, communication protocols, and what happens when software meets the physical world.

• You can debug across layers. When something is slow or broken, you can trace it from application code down to system-level issues.

• You write code that runs unsupervised. Edge systems can't crash and wait for someone to restart them.

• You figure things out. Niche hardware, undocumented APIs, weird edge cases in warehouse environments. You dig in.
  

Nice to have

• Experience with computer vision or perception systems. Camera calibration, image processing, video encoding/decoding, inference pipelines.

• Background in robotics or autonomous systems. You've built software that interacts with the physical world in real time.

• Experience with edge compute platforms and AI accelerators.

• You've worked with AI/ML model deployment on device. Model optimization, quantization, inference runtimes.

• Linux systems programming.

• Experience shipping hardware products. You know the difference between a demo and a deployment.
  

What we offer

• Base salary plus equity. A real stake, not a token grant.

• You'd build the real-time systems at the core of a product that's deployed and working in warehouses today.

• Direct access to founders and the hardware team. No layers between you and decisions.

• Hard problems. Real constraints. Software that has to work in the physical world.

• A small team where your work is visible and your opinions matter.
  

Comp

We want someone who bets on themselves. If you're optimizing purely for guaranteed base, this probably isn't the right fit. If you want equity in a company where your engineering directly determines product quality, this structure works.

How to apply

Send us two things:

1. A system you've built or worked on where performance mattered. What were the constraints, what tradeoffs did you make, and how did it perform?

2. You have a camera feed, an AI model running on an edge device, and results need to reach a dashboard with minimal latency. Walk us through your architecture. Keep it under a page.