In Your Job:

• You’ll ship end-to-end AI-powered product features — from prototype to production — balancing speed during exploration with quality in what’s delivered.

• You’ll work as a full-stack engineer (Next.js, TypeScript, Tailwind, tRPC, PostgreSQL, Vercel) while seamlessly weaving in AI capabilities.

• You’ll own AI-driven product decisions: when to use RAG, fine-tuning, pgvector, embeddings, or new SDKs — always pushing for cost-awareness, performance, and maintainability.

• You’ll actively contribute code, remove blockers for others, and keep communication crisp so the team moves smoothly.

• You’ll make our AI practices stronger by codifying learnings (context window mgmt, prompting, evaluation, scaling strategies). (or creating systems for living documentation that helps for knowledge sharing).

• You’ll collaborate in a decentralized leadership setup: independent, hands-on, yet aligned to make apex a multiplier for the org.

For a "perfect match," you need:

• Strong TypeScript & modern full-stack skills (Next.js, Tailwind, tRPC, PostgreSQL, Vercel).

• Experience building AI-enabled applications with modern LLMs (GPT, Claude, etc.) and vector databases (pgvector).

• Proven ability in prompt engineering, context-window handling, and practical application of LLM best practices.

• Comfort making tradeoffs in AI product architecture (cost vs. speed vs. maintainability), plus curiosity to explore what’s next.

• A self-responsible work style, strong communication, and bias to ship.

• Attitude-first: startup hacker mindset with respect for both speed (for prototyping) and quality (for shipping).