About the role
Centh is building the intelligence layer for critical frontline workforce management.
Frontline workers move between shifts, facilities and locations, and every assignment brings its own qualification and compliance requirements. Today that work runs on manual handoffs across disconnected systems, which slows deployment and drives up cost.
Our AI agents run these workflows across the systems organizations already use:
- Recruiting: sourcing, screening and submitting candidates.
- Onboarding: building requirement checklists, verifying documents and licenses, and following up on outstanding steps.
- Continuous compliance: monitoring credentials and running primary source verification.
We are an early-stage team based in New York.
Software EngineerLocation: New York, NY · Type: Full-time
Work authorization: This role is open only to candidates who are already authorized to work in the United States without visa sponsorship, now or in the future. Centh does not sponsor, transfer or extend work visas of any kind, at any stage of employment. If you will need sponsorship at any point, including when a temporary work permit expires, please do not apply. Applications that misstate work authorization will be removed from consideration.
Our agents are only as good as the systems around them. You will build the integrations, data layer and product surfaces that let agents read and write across every system an organization runs, and that let operations teams see and steer what the agents are doing.
What you'll do- Build reusable integration adapters for applicant tracking, vendor management and HR systems: webhooks, ingestion, writeback and reconciliation, with source identifiers and freshness tracked on every record.
- Own pieces of our shared data model: a single source of truth for workers, roles, requirements and documents that every agent and every customer runs on.
- Map each customer's requirements and document types onto that model through configuration, so onboarding a new customer or industry needs no code fork.
- Build product across our web platform, our Chrome side-panel extension and our worker portal, including the views operations teams use to review, filter and hand off agent work.
- Build shared email and SMS infrastructure, workflow controls and agent oversight tools.
- Run scheduled and event-driven jobs, such as continuous compliance checks, reliably at scale, with retries, idempotency and clear failure alerts.
- Build live metrics and regression dashboards that compare agent decisions against human decisions and across system versions.
- Harden auth, permissions and audit logging around sensitive worker data.
- 1+ years building and running production software, end to end.
- Strong TypeScript, with real experience in React on the front end and Node.js on the back end.
- Solid SQL and relational data modeling, including migrations on a live system.
- Experience integrating third-party APIs where the docs are thin: webhooks, rate limits, retries, idempotent writes and reconciling two systems that disagree.
- You debug from logs and data, not guesses, and you leave systems more observable than you found them.
- Product sense: you talk to the operators using what you build and change it based on what you see.
- Comfort working in a small team where scope shifts and you own outcomes, not tickets.
- Chrome extension development (Manifest V3, side panel).
- Experience with Vercel, serverless and durable workflow or queue systems, plus caching (for example Redis).
- Integrations with ATS, VMS, HRIS or scheduling platforms.
- Experience building LLM features, or working closely with engineers who do.
- Background in workforce management, staffing or compliance software.