Job Description

Job Description
Looking for a software engineer with experience delivering production-ready LLM services. The position involves transforming data into fast and reliable recommendations, operating artificial intelligence systems that support the platform and collaborating on new projects based on this technology.
Responsibilities:
Manage the complete delivery of LLM services in production.
Turn complex data into fast, reliable recommendations at scale.
Build and operate AI systems that support the platform with production-grade performance.
Collaborate with several teams on different projects based on this infrastructure.
Requirements:
4-6 years of software engineering experience in product environments, including at least 2 years implementing LLM/GenAI in production.
Demonstrable experience managing services from start to finish (design, implementation, deployment, monitoring and iteration).
Ability to communicate clearly and make pragmatic decisions, collaborating with Mobile, Backend and Operations teams (Dev/LLM).
Experience with technologies:
Languages and APIs: Python (FastAPI), TypeScript (Node/Nest BFF), REST/GraphQL, WebSocket/SSE.
Production experience with Python + FastAPI (async, dependency injection, testing).
Integration with TypeScript/Node.
Building APIs with REST/GraphQL and at least one streaming pattern (SSE/WebSocket).
LLM and RAG: embedding stores (pgvector / OpenSearch / etc.), chunking strategies, re-rank, hybrid search, prompts and templates tools; guardrails.
Observability and quality: structured logging, tracing, metrics; experimentation and evaluation tools (e.g. Langfuse-style telemetry), offline/online A/B testing.
Data and pipelines: robust CSV/Sheets ingestion, schema validation, PII management, backfills, scheduled jobs.
Experience with agents: familiarity with MCP and agent frameworks, tool design, controlled execution and secure planning.

Salary to receive
€5,100 - €8,800 / month