rothific

Mozilla / Thunderbird / Thunderbolt | Staff Product Engineer, Enterprise AI | REMOTE (US or Canada) | Full-Time | $185K–$220K USD / $155K–$185K CAD | https://grnh.se/viz7vum71us

We're building Thunderbolt (https://github.com/thunderbird/thunderbolt). We're an 8-person and growing team within the ~60-person company behind Thunderbird, the open-source email client used by 20M+ people.

Thunderbolt is an open-source, cross-platform AI product built on the principle that people and organizations should be in control of their data, infrastructure, and model choices. It's moving from early development into enterprise use cases, and we need someone to own features end to end — concept through launch, adoption, and iteration — not just close tickets.

You'd work full-stack on AI-powered chat, search, research, workflow automation, admin, and integrations. We're looking for 10+ years of engineering experience at Staff scope, hands-on AI product work (LLMs, RAG, agents, retrieval, model/provider abstraction), and comfort in ambiguity — architecture and enterprise requirements are still being defined. Bonus: self-hosted or regulated deployments, EU AI Act / GDPR / SOC 2 familiarity.

Must reside in and have work authorization for the US or Canada. No sponsorship. We read every cover letter - please make it authentic.

This is really cool!

Essentially version controlled A2A.

I'm exploring a bunch of agent protocols right now and experimenting with a similar concept for context syncing over git here: https://github.com/cjroth/csp

Updated!

Fair point :)

Thunderbolt was funded from a grant, not donations.

https://github.com/thunderbird/thunderbolt/blob/main/docs/fa...

It's not. Mozilla has been more than Firefox for a long time.

Hi, I'm on team that worked on this. No it's not vibe coded. We do pretty intense code review of every PR. It looks like the number you're seeing is including lock files and artifacts that are not part of the core coverage.

I think that wasn't phrased well- it's "revenue" positive meaning donation money covers more than the expenses

Stop spreading misinformation, it's funded by grant money https://github.com/thunderbird/thunderbolt/blob/main/docs/fa...

I've been experimenting with running Gemma with MLX directly within my own harness: https://github.com/cjroth/mlx-harness

I agree. Also, very different world from Rust, but shadcn has popularized this for UI components and AI skills are done this way frequently.

I'm excited to see more patterns like this for other types of code.

Websockets would work great actually! Basically anything would work as long as you don't use any node or bun specific imports. For file systems you could also use something like this https://github.com/isomorphic-git/lightning-fs

I'm glad you think the try before install scenario makes sense - I think this is definitely the main use case.

Yep, mainly performance - specifically page load time (near instant for Gridland vs ~2-3s for Ink Web). The other issue was flickering. Tbh rendering directly into a canvas is just a better approach and OpenTUI's architect is more modern.

I love that xkcd, I never know what to do, so I'll just ：）)

You should be able to. We forked OpenTUI in order to avoid having to shim a bunch of native stuff. I'd like to make it compatible - email me at [email protected] if you find a way or want any help making it work

Does anyone know if this is mainly going to affect people in Cary, NC?

Nice! I made a proof-of-concept of using Ink + Ghostty Web a few months back - we didn't end up merging it, but it's still an interesting thing that's possible. I think Ghostty Web is also has tons of potential.

https://github.com/cjroth/ink-web/pull/1

Yes (if you're also down to use React)

Thank you! I'm glad you think so. It's all about fun.