T

Senior AI Engineer (LLM Feature Development)

technical inside Iasi Metropolitan Area
Remote
Apply
AI Summary

Design and deploy end-to-end LLM-powered features, including prompt engineering, retrieval systems, and production guardrails. Collaborate with clients to define data and budget constraints while ensuring safe, scalable integrations. Requires 3+ years of applied AI and production software experience with Python/TypeScript.

Key Highlights
End-to-end ownership of LLM-backed product features from prompt design to API/UI implementation
Focus on safety, evaluation, and guardrails for production-grade AI systems
Direct client collaboration for scoping data and budget constraints
Key Responsibilities
Design and ship LLM-backed product features, covering prompt strategy, context design, and API/UI integration
Build and maintain MCP (Model-Centric Platform) servers and tool integrations for safe agent-system interactions
Implement evaluation, tracing, and guardrails to ensure feature reliability in real-world user scenarios
Work closely with clients during discovery to define feasible data and budget constraints
Technical Skills Required
Python TypeScript Retrieval-Augmented Generation (RAG)
Benefits & Perks
Fully remote work (Romania-based applicants only)
Nice to Have
Experience with local/open-weight models (e.g., llama.cpp, GGUF, vLLM)
Familiarity with vector databases, fine-tuning, or structured-output/evaluation tooling
Background in privacy or document-AI

Job Description


← All open roles

Careers

AI Engineer

Iași / Remote (Romania)

  • Full-time

We build applied AI that ships — like Censory, which detects PII and truly strips it from a PDF, not just draws a black box. You will own LLM-backed features end-to-end: prompt design, MCP tooling, retrieval, evaluation, and the guardrails that keep them honest in production.

This role is fully remote — applicants must be located in Romania. The company is based in Iași.

What you'll do

  • Design and ship LLM-backed product features — from prompt and context strategy to the API and UI they live behind
  • Build MCP servers and tool integrations that let agents act on real systems safely
  • Stand up evaluation, tracing, and guardrails so features hold up with real users, not just in a demo
  • Work directly with clients during discovery to scope what their data and budget can actually support

What we're looking for

  • 3+ years shipping production software, with real applied-LLM feature work behind you
  • Strong Python and/or TypeScript, and comfort wiring models into web and product surfaces
  • Hands-on with RAG, function/tool calling, or agent orchestration in something that shipped
  • Fluent enough in English to run discovery and delivery with international clients

Nice to have

  • Experience serving local / open-weight models (llama.cpp, GGUF, vLLM) and the MCP ecosystem
  • Vector databases, fine-tuning, or structured-output/eval tooling
  • A privacy- or document-AI background

Apply for this role

Fill out the form below — the position is already pre-selected for you.

Similar Jobs

Explore other opportunities that match your interests

Software Engineer - Stablecoin Team

Programming
2m ago

Premium Job

Sign up is free! Login or Sign up to view full details.

•••••• •••••• ••••••
Job Type ••••••
Experience Level ••••••

Coinbase

Canada

Senior Software Engineer, Stablecoin Platform

Programming
6m ago

Premium Job

Sign up is free! Login or Sign up to view full details.

•••••• •••••• ••••••
Job Type ••••••
Experience Level ••••••

Coinbase

United State

Full Stack Engineer

Programming
4h ago
Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Mid-Senior level

hyra

United Kingdom

Subscribe our newsletter

New Things Will Always Update Regularly