San Francisco, CA · On-site · Full-time Compensation: $150,000–$300,000 + 0.1%–1% equity

Our client converts complex documents into LLM-ready data. Production-grade APIs ingest, parse, structure, and split documents across formats like PDF, PPT, and Excel into clean Markdown and JSON that AI agents and LLMs can reliably work with from day one — preserving document structure and hierarchy while capturing the domain-specific context critical for high-stakes workflows across finance, legal, and healthcare.

Founded 2024 · 1–10 people (Seed) · Industry: AI Tools

A Founding Software Engineer based in San Francisco, building toward a small, talent-dense team. The role is backend- and infrastructure-heavy: own production systems end to end and turn research prototypes into production-grade, scalable systems alongside the founders and research team.

Tech stack: Python (required); C++/Rust (plus); distributed systems (microservices, queues, Redis); cloud (AWS/GCP/Azure); Docker, Kubernetes, Helm; Terraform / Pulumi.

• 2–5 years of experience
• Able to work in person at the San Francisco office
• Hands-on experience building backend infrastructure

• A top-tier school background (e.g., IIT Bombay, Stanford)
• Very early-stage startup experience (first 1–3 engineers)
• Experience at companies with strong technical DNA
• Research experience

• A founding technical seat: this role defines the engineering archetype and sets the technical ceiling for the team
• End-to-end ownership: own the full stack from core backend architecture and infrastructure through deployment, reliability, and developer experience
• Real enterprise traction: already deploying production AI for enterprise customers across high-stakes verticals

• Location — San Francisco, CA
• Work policy — On-site
• Compensation — $150,000–$300,000 + 0.1%–1% equity
• Visa sponsorship — Available (H-1B, O-1, OPT)
• Employment type — Full-time