About the role
We run the platform and local inference on machines we control. You own that layer: Linux hosts and images, firmware and boot, kernel and driver work where a device needs it, GPU and NPU bring-up for local models, performance and reliability without a cloud abstraction between you and the hardware. Snaga Code is your pair on the platform; the deploy pipeline is yours to harden.
Working with AI — your co-executors
Snaga Code is your pair on the metal layer: it drafts provisioning scripts, kernel configs and driver scaffolding in your repo; you review, test on the real hardware and sign. Platform agents watch the fleet's observability under your rules and draft incident notes; bring-up decisions and anything that touches production hosts are yours.
You are not using AI tools; you are working in a team where AI agents are co-executors. Every role at Snaga has its own pod of agents on the Snaga AI platform: a Planning agent that turns a brief into a plan, Builder agents that do the first pass of the work, a QA agent that checks it, and a Knowledge agent that answers with citations from our documents. Agents plan and execute; the person sets the goal, reviews the result, signs every action that leaves the sandbox, and teaches the agents where they were wrong. Every step is in an immutable audit log, so you always see what the agents did and why.
Our tools, exclusively
All work and all training happen on Snaga's own instruments: the Quark browser, the Snaga AI orchestration platform and the Svitlo agent. Quark delegates work by conversation — to the Snaga Code agent for development and to Svitlo for information research — keeps every account in its own isolated profile, and asks for your explicit approval before anything touches passwords, e-mail, payments or deletions. On the platform your work runs as agent teams (Planning, Builder, QA, Knowledge) in a Plan→Build→QA→Deliver→Learn loop; every action that leaves the sandbox waits for a human signature, every step is in an immutable audit log, and knowledge agents answer with citations. You will be trained on these tools in your first weeks and you will help make them better.
How we work
Remote-first, async by default, with a weekly review. Tooling is ours; equipment is on us.
What you will do
- Own Linux host images, boot, firmware and kernel configuration for our fleet
- Bring up and tune GPU/NPU inference boxes for local models
- Write and debug low-level code in C and Rust where the hardware needs it
- Own performance, observability and reliability of the metal layer
- Automate provisioning and the deploy path with the Snaga Code agent
- Work with AI agents every day as co-executors: brief them, review their output, sign what matters, and teach them where they were wrong
What we expect
- 5+ years in systems or embedded engineering on Linux
- C and Rust; comfortable in the kernel and with drivers
- Hardware bring-up, firmware, boot chains, debugging with real probes
- Docker, networking and storage at the host level
- Readiness to work and train exclusively on Snaga's tools: Quark, the Snaga AI platform and the Svitlo agent
- Comfort working alongside AI agents as co-executors: delegating, reviewing their output critically, and taking responsibility for the signed result
- English B2 or higher
Nice to have
- GPU/CUDA or NPU runtime experience
- Rust in production
What you get
- Remote, flexible hours
- Equipment and tooling budget
- Paid training and certifications
Skills
- Linux
- C
- Rust
- Firmware
- Kernel
- GPU bring-up
- Docker
- Snaga Code