AI Platform Engineer (m/f/d)
Core
Design, build, and operate the technical platform for AI/LLM applications, focusing on infrastructure, reusable components, and cost efficiency.
Role type
Senior AI Platform Engineer (Infrastructure & Operations)
Builds
Model hosting, inference gateways, and production-ready AI solutions for internal teams.
Domain
AI/LLM Infrastructure, Cloud Operations, .NET Ecosystem
Deliverable
production ML models
Required skills
LLM inference frameworks (vLLM, Ollama, llama.cpp, TGI), Self-hosted LLMs, C#/.NET, Docker, CI/CD, API Gateways, Cost optimization
Preferred skills
Python, React, GPU infrastructure, ETL/ELT
Technologies
C#, .NET, Python, React, Docker, vLLM, Ollama, llama.cpp, TGI, LiteLLM
Responsibilities
Evaluate and operate local/self-hosted LLMs with quantization and resource sizing; manage AI consumption and costs; establish frameworks and guardrails for the team; transition prototypes to production; handle CI/CD and monitoring for AI solutions.
Seniority
Senior, hands-on IC
