Full Stack DEV + AI Engineer

Level: Mid / Senior

About the role
We're looking for a versatile Full Stack AI Engineer who can own features end-to-end — from pixel-perfect React/TypeScript interfaces, through scalable Python/Node/Go backends, all the way to integrating, fine-tuning and shipping LLM-powered experiences that feel magical to users.

This is not a pure ML research position. You will spend most of your time writing production-grade code, designing reliable AI workflows (RAG, agents, tool-calling, evals), and making sure AI features are fast, cost-effective, observable and safe.
You will

Design & build full user-facing AI-powered features (chat interfaces, copilots, content generation tools, intelligent search, recommendation systems, document understanding flows, etc.)

Integrate LLMs (OpenAI, Anthropic, Grok, Llama-3.x/4, Mistral, etc.) via APIs and/or self-hosted models
Implement robust RAG pipelines, prompt engineering, function/tool calling, agent orchestration
Own frontend (React / Next.js / Svelte / Vue) + backend (Python FastAPI / Node.js / Go / Django) + infra glue (Docker, Kubernetes / ECS, serverless, PostgreSQL / vector DBs)

Collaborate closely with product, design & data science to turn vague ideas into reliable, delightful AI experiences
Set up evaluation frameworks (human + LLM-as-judge), A/B testing, usage monitoring, cost tracking & safety guardrails
Improve latency, token efficiency, reliability and cost of AI features in production
Participate in on-call rotation for critical AI-powered services

Must-have skills & experience

4–7+ years of production full-stack development experience

Very strong modern JavaScript/TypeScript (React + Next.js / Remix / app router strongly preferred)
Solid backend experience with at least one of: Python (FastAPI/Pydantic), Node.js, Go
Hands-on experience shipping LLM-powered features to real users (OpenAI API, Anthropic, Grok, LangChain / LlamaIndex / Haystack / DSPy / smolagents, etc.)

Practical understanding of RAG, prompt chaining, tool use / function calling, agent patterns
Experience with vector databases (Pinecone, Weaviate, Qdrant, PGVector, Chroma)
Comfortable with cloud platforms (AWS / GCP / Azure) — especially serverless, object storage, managed Postgres/vector DBs
Git + clean commit hygiene, PR reviews, CI/CD basics

Strongly valued (nice-to-have / big plus)

Production experience with fine-tuning or LoRA / QLoRA (even small/medium models)
Experience with evaluation & red-teaming of LLMs
Observability for AI systems (LangSmith, Phoenix, PromptLayer, Helicone, OpenLLMetry)
TypeScript backend (tRPC, NestJS, Hono, Elysia)
Experience building AI agents or multi-step reasoning systems
Previous startup / high-growth product environment

What we offer

Competitive salary + meaningful equity
Flexible working hours & remote-friendly culture
Budget for top-tier AI API credits / self-hosted GPU experimentation
Strong focus on learning — conference budget, books, courses, internal tech talks
Small, senior team — high ownership, low bureaucracy

To stand out
In your application / cover letter, please include:

One AI-powered feature or product you personally built and shipped (what problem did it solve, which models/tech did you use, what was hard about it?)

A recent piece of code you're proud of (GitHub link, gist, or short description is fine)

We're excited to meet engineers who can both craft beautiful UIs and make LLMs behave reliably at scale.
Apply now or share this with someone who lives at the intersection of full-stack craftsmanship and applied AI.