Senior AI/LLM Platform Engineer

We’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 bring

• 5+ 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-have

• LLM gateways and routing (e.g. LiteLLM) and LLM observability.

The impact you'll create

• Design 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.