Comment by charlesleft

4 hours ago

We're a small, research-driven, VC-backed team building NeoHuman: a desktop-first system that observes how people actually use AI tools, files, and workflows during real tasks, and turns those sessions into reliable evaluation evidence. We care about the process, not just the final answer — what someone typed, what they copied, what they verified, how they moved across apps.

We've published the AgentIF-OneDay benchmark. Now we're scaling the capture and evaluation infrastructure underneath it.

You'd own: - Cross-platform desktop capture across macOS + Windows (AX/UIA trees, OCR, clipboard, keyboard/mouse boundaries, file interactions) - Trace fusion — turning noisy low-level signals into clean human-readable session timelines - The evaluation evidence pipeline (data model, ingestion, exports) - LLM normalization that summarizes traces without hallucinating or hiding evidence quality - Privacy/consent/proctoring safety for enterprise customers

We want an AI-native engineer: - 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) - Uses Claude Code, Cursor, or similar as a daily working medium — not a side experiment - Bonus: macOS AX / ScreenCaptureKit / CGEventTap, Windows UIA, or you've studied/built things like 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.