Join a fast‑moving team building production‑ready AI‑native applications with full‑stack tech. You’ll co‑create code alongside advanced AI assistants, turning specs into functional systems at speed and quality.
What You’ll Do
- Build and scale AI‑native apps from prototype to production.
- Translate product requirements into working code using AI‑assisted tools.
- Design full‑stack solutions—frontend, backend, and APIs.
- Integrate LLMs, RAG pipelines, and embeddings into real‑world features.
- Optimize performance, cost, and reliability with AI‑driven insights.
- Use Copilot, Cursor, Claude, LangChain, or LlamaIndex to accelerate development.
What You Need
- Strong Python (preferred) or Node.js/JavaScript backend development.
- Experience building REST or GraphQL APIs.
- Proficiency with React or similar frontend frameworks.
- Hands‑on with LLM APIs (OpenAI, Anthropic) and prompt engineering.
- Familiarity with cloud platforms (AWS/GCP/Azure) and deployment basics.
- Ability to think product‑first, focusing on user impact and cost efficiency.
- Experience debugging and optimizing AI‑integrated full‑stack systems.
Good to Have
- Built agent‑based workflows or internal copilots.
- Developed benchmarking frameworks for LLM quality, latency, and cost.
- Implemented LLM proxy patterns like routing, caching, and safety filters.
- Experience in fast‑paced startup or product environments.
The Opportunity
The role emphasizes AI‑assisted development, where code is co‑created with tools like Copilot and Claude, and expects you to handle end‑to‑end production workloads.