Senior AI/LLM Platform Engineer

Avenga is an international engineering firm helping businesses operate with AI at the core. With 6,000+ experts worldwide, we combine engineering expertise with AI-native thinking to turn ambitious ideas into real-world impact across industries, technologies, and markets. At the core of the roleWe’re looking for an experienced platform engineer to build and run the environments where our AI runs. You will set up on-premise and cloud LLM platforms, deploy and serve open-weight models, optimize them to run efficiently on GPUs, and administer the platform as it grows.Your platform will power AI-native engineering and business use cases across client projects. You will work hands-on with GPU infrastructure and modern inference stacks, with room to explore new models, inference engines and hardware as the field evolves.Core skills you’ll bring5+ years of experience in platform engineering, DevOps, infrastructure, or ML infrastructure.Hands-on experience deploying and serving open-weight models (e.g. Llama, Qwen, Mistral, Gemma) with inference engines such as vLLM, SGLang, Ollama/llama.cpp.Practical knowledge of inference optimization, such as quantization, batching and multi-GPU deployment, and matching models to available hardware.Experience with GPU infrastructure - NVIDIA drivers and CUDA, GPU scheduling on Kubernetes, and monitoring GPU utilization.Experience with on-premise infrastructure and at least one cloud provider (AWS, GCP or Azure), including their GPU and AI services.Strong Docker and Kubernetes skills and infrastructure as code (Terraform/OpenTofu).Hands-on experience with at least one modern AI coding tool, such as Claude Code, Codex, Cursor or GitHub Copilot.Fluent English.Nice-to-haveLLM gateways and routing (e.g. LiteLLM) and LLM observability.The impact you'll createDesign and build on-premise and cloud environments for hosting LLMs.Deploy, serve and scale open-weight models behind standard APIs (e.g. OpenAI-compatible endpoints).Optimize models and serving configuration for throughput, latency and GPU cost, and benchmark the results.Administer the platform: upgrades, capacity planning, access control, quotas and the model catalog.Monitor performance, GPU utilization, usage and cost.Evaluate new models, inference engines and hardware, and recommend what to adopt.Secure the environment, including isolating client data and controlling access.Support engineering teams and AI agents that use the platform.People are at the core of Avenga. We provide equal opportunities regardless of race, ethnicity, gender identity, sexual orientation, disability, age, religion, or any other characteristic. We are committed to a respectful environment where everyone can be themselves, share their ideas, and feel that they belong.