What you will do
Design and ship full-stack features on top of LLM APIs, RAG pipelines and agent workflows.
Translate a business requirement into a technical approach and drive it without waiting to be told the next step.
Work directly with clients: understand the problem, propose the approach, defend the trade-offs.
Keep evaluation, latency and cost in view. A demo that cannot hold production traffic is not done.
Review each other’s work properly. Small team, high standard.
What we are looking for
AI and full stackHands-on experience building modern full-stack applications with real exposure to generative AI and LLM-based solutions.
Solution ownershipYou can read a business requirement, design the technical approach and drive it to delivery independently.
Client-facing skillsComfortable working directly with clients, presenting an approach and handling the follow-up questions.
Engineering mindsetStrong problem-solving, system design and fundamentals, so you can work without hand-holding.
EducationCandidates from top-tier engineering and technology institutions preferred, but the work speaks louder.
Technology stack
AI & LLMLLM APIs · RAG · AI agents · Prompt engineering · Vector databases
BackendPython · FastAPI · Node.js · NestJS
FrontendReact · Next.js · TypeScript
DataPostgreSQL · Redis · Vector DBs
Cloud & DevOpsAzure · AWS · Docker · Kubernetes · CI/CD
IntegrationREST APIs · Microservices · Enterprise integrations
Send a CV and a short note on something you built and had to keep running to jobs@zitrino.com. Put the role title in the subject line. We read every application ourselves and reply either way, usually within a week.