Software Engineer, Ori
This is the employer's own posting, not a copy on a job board.
What we know
Is it still open?
Confirmed still open
Last checked 21h ago — checked against the employer's own applicant tracking system, which is the company answering directly.
We re-read the employer's own applicant tracking system and the posting was still there. That is the company answering directly.
How old is it?
Posted 4d ago
The date the source published, not the day we noticed it (2026-10-06). Last seen at its source 2h ago.
We have tracked this listing since 7 Oct 2026 (4 days). The employer's own board has carried it every time we have read it, most recently 2 hours ago.
Is it remote?
Remote (US)
That is the location the employer filed this posting under. Quoted as written — we do not re-word the source's own location.
Who may apply?
United States
The description states no restriction of its own. This is the source's own tag.
Pay not stated
Similar roles pay $150k–224.6k/yr
Middle 50% of 4031 listings that do state pay — Engineering · all levels · United States · USD/year. This employer has published no salary; this is what comparable listings we hold disclose, never converted between currencies or periods. How this is calculated.
Skills named in the ad
Recognised terms only, from a fixed vocabulary — this is what CV matching compares against.
Carried by 1 source
-
Ashby employer's own board first seen 4d ago · last seen 2h ago
The listing
About OpenRouter
OpenRouter is the leading AI routing and infrastructure layer that enterprises use to access, manage, and optimize the best large language models across providers—without lock-in, capacity constraints, or unnecessary cost. We power the most advanced AI teams in the world by giving them the flexibility to move fast, scale confidently, and stay future-proof as models evolve.
As enterprise adoption of AI accelerates, OpenRouter sits at the center of how organizations operationalize LLMs across research, product, and production workloads.
About the Role
We're hiring a Software Engineer on our Ori, to build out our family of products for putting any model to work in your terminal, in Slack, and on your desktop. Ori is built to answer the question from large buyer ICP, we are building the client side products for massive enterprise adoption of OpenRouter beyond the engineering organization.
Ori is small team built the current product in a few months. You'll work with that team, which is led by one of our co-founders, alongside product, design and the platform teams Ori is built on. This is a hands-on IC role with broad surface area and little process between you and shipping.
What You'll Do
Build and ship across every Ori surface: the
oriCLI and its harness integrations.Make model fungibility real in any harness. That means model switching, provider fallbacks, tool and prompt settings tuned to each model, and respecting org guardrails, all without extra auth for the user.
Build the agent runtime underneath. That includes sandboxed agents that never see their own credentials, secrets management, session management and compaction, and skills that agents can learn, share and inherit across models.
Take agents from a laptop to the cloud: deploy, fork and shut down agents on command, with agent state that is version-controlled and auditable.
Own quality end to end, from install, auth and CLI UX to reliability, observability and evals. Ori is heavily dogfooded internally, so you'll use what you build every day.
Feed the gaps Ori exposes back into OpenRouter's API and SDKs, so the whole ecosystem can build multi-model agents on the same primitives.
What We're Looking For
5+ years shipping production software, with real ownership of developer tools, CLIs, agent products or the infrastructure behind them.
Daily fluency with coding agents like Claude Code, Codex, OpenCode, Pi or Hermes, and specific opinions about what makes an agent loop, a harness or a tool integration good.
A solid grasp of how agents work under the hood: tool calling, context management, prompt caching, evals, and the cost, latency and quality tradeoffs between models.
Good systems judgment for running agents safely: sandboxing, process isolation, secrets, and reliability across many users.
High agency and a bias toward action. You talk to users, prototype, ship and iterate on a small team with fluid boundaries.
Product taste for developer tools. You notice interaction details and care how the first five minutes feel.
Nice to Have
Built or maintained an open-source agent harness, CLI or developer tool. Experience with multi-agent systems, agent skills or memory, or eval and benchmarking tools.Shipped a Slack app or a native macOS app.Existing user of OpenRouter or Ori, or active side projects in AI tooling.
If you don't think you meet all of the criteria above but are still interested in the job, please apply. Nobody checks every box, and we're looking for someone excited to join the team.