Job Description

Role overview: You will own cross-platform desktop capture across macOS and Windows (AX/UIA trees, OCR, clipboard, keyboard/mouse boundaries, file interactions); trace fusion to turn signals into clean session timelines; the evaluation evidence pipeline (data model, ingestion, exports); LL M normalization that summarizes traces without hallucinating or hiding evidence quality; privacy/consent/proctoring safety for enterprise customers. Requirements: 3+ years shipping production TypeScript + Node.js; built or shipped Electron + native helpers; strong PostgreSQL (schema design, indexing, data quality); comfortable with OS APIs, permissions, background processes; hands-on LLM API experience (structured output, evaluation, hallucination control); daily use of Claude Code, Cursor, or similar as a working medium; bonus: macOS AX / ScreenCaptureKit / CGEventTap, Windows UIA, or prior work on Screenpipe, OpenAdapt, Rewind, OpenChronicle. Stack: TypeScript · Node.js · Electron · native macOS/Windows · Next.js 15 · React 19 · Postgres + Supabase · OCR · Accessibility APIs · OpenAI / Anthropic / Gemini · Vercel · GitHub Actions. Why us: hard, unusual problem at the boundary of OS internals, multimodal capture, and AI evaluation. Small team, technical founders who code daily, real ownership of the capture stack. We hire on demonstrated capability, not credentials. Apply: email jack@emergences.ai with your resume and a brief note about a system you’ve built — desktop software, AI infra, data pipelines, evaluation, or low-level debugging. Subject: "Your Name — AI / Systems Engineer". Please mention HN in the email. Full JD: https://emergences.ai/careers/ai-engineer