AI Engineer - Croatia
Core
Build, own, and operate production-ready LLM-powered services end-to-end for B2B clients, enabling accurate, data-grounded recommendations and intelligent workflows.
Role type
Senior IC AI Engineer (LLM/GenAI)
Builds
Production-grade AI systems and platform features
Domain
B2B SaaS, Large Language Models, Retrieval Augmented Generation
Deliverable
production ML models
Required skills
Python (FastAPI), TypeScript (Node/Nest), REST/GraphQL, WebSocket/SSE, embedding stores, chunking strategies, re-ranking, hybrid search, prompt engineering, guardrails, structured logging, tracing, metrics, experiment/eval tooling, CSV/Sheets ingestion, schema validation, PII handling, backfills, scheduled jobs, agentic workflows, MCP, tool design, constrained execution, Docker, Kubernetes, CI/CD, model gateways, object storage, message bus, tenant-aware access controls, secrets management, audit logs
Preferred skills
LLM serving optimization (vLLM, TensorRT-LLM), quantization, LoRA, retrieval eval frameworks, cross-encoder rerankers, response grading, cost controls, token budgeting, prompt compression, security and privacy red-teaming
Responsibilities
Design, implement, roll out, monitor, and iterate on end-to-end AI services; integrate LLMs with existing backend systems; manage data pipelines and evaluation frameworks; optimize model serving and inference costs; ensure system reliability and observability
Seniority
Senior, hands-on IC