This listing does not state pay. Across 166 open senior listings that state pay, the middle half runs $180,000 to $260,000 and the median is $225,000.

Listed pay is what employers advertise, not what people are paid.

Senior salaries by state · Check your own pay

How AI is used in this kind of work

Among software developers, AI is already used for some of the tasks. Measured exposure for software developers: 29% (some).

Share of this job’s tasks that AI is already used for at work, from real usage. It is not a forecast of job loss, and a low number means no use seen yet. Source: Anthropic Economic Index.

Check how this applies to your own job

Skills this job asks for

Say which you have and which you want to build. We use it to match you to jobs like this one.

About the job

About Sandbar

Sandbar is an interface company in New York City. We aim to expand human thinking. Our team has built software, ML, hardware, and consumer products across Meta, CTRL-labs, Apple, Peloton, and Equinox.

Our first product is Stream, is private voice ring that extends your thinking. Stream has been featured in WSJ, Bloomberg, Wired, and Time's Best Inventions of the Year.

Join us in creating technology that extends human thinking.

About We’re looking for a strong generalist engineer to connect Stream to the software people already use. Stream is a self extension that listens, remembers, and helps you think through conversation, and the more of your world it can reach, the more useful it becomes.

Most software wasn’t built to work with an AI. Making it work means understanding how each application is built, finding the most reliable way in, and making that connection dependable for people who rely on it every day. You’ll own this work end to end, work directly with the founders, ship on the same real-time Python services the rest of Stream runs on, and help shape how others build on Stream.

Responsibilities

Build integrations between Stream and the apps, services, and AI tools people already use

Design how tools plug into Stream’s agent: tool definitions, result shaping, confirmation, and context passing

Own the integration layer end to end: OAuth and token lifecycle, least-privilege scopes, webhooks, rate limits, retries, and real-world failure modes

Build and operate MCP servers and clients in production

Work out reliable integrations for software without clean APIs

Instrument every integration so breakage is caught before users notice

Carry a share of the core backend and its on-call rotation

Qualifications

5+ years building software, with strong Python and comfort owning a live, real-time service

Have shipped third-party integrations in production: OAuth 2/OIDC, token refresh and revocation, webhooks, API versioning, and vendor quirks

Understand software architecture well enough to work with applications you didn’t write

Have integrated tools into an LLM agent that real users depend on, and been accountable for actions completing

Hands-on MCP experience

Generalist range across backend, auth, client code, and agent logic; can take an open-ended problem to a shipped result without a spec

Product sense for software that acts on someone’s behalf, including when the user isn’t looking at a screen

Communicate precisely and make tradeoffs explicit

Nice to have

Connector or plugin work at an AI product

Browser automation (e.g. Playwright, Chrome DevTools Protocol)

Integration security: scoped credentials, secret storage, prompt-injection defenses, audit logging

Voice or multimodal assistant experience

Developer documentation other engineers have built on

FTE Benefits

Health, vision, and dental benefits

Company-sponsored 401(k)

Unlimited PTO and sick time

Early stage equity