AI Engineer (LLM Infrastructure)

Role overview

• check_circle Own and manage our heavy-compute AI hardware, specifically optimizing workloads for our Nvidia HGX H200 infrastructure.
• check_circle Deploy, fine-tune, and maintain open-source LLMs, ensuring maximum throughput and minimal latency.
• check_circle Manage inference engines (e.g., vLLM, TensorRT-LLM) and handle dynamic GPU memory allocation for hundreds of concurrent agent requests.
• check_circle Provide a flawless, millisecond-response API layer for our "OpenClaw" agent farm (a fleet of 200+ bare-metal Apple Silicon nodes).
• check_circle Monitor model performance, detect hallucinations, and build synthetic training data pipelines to continuously improve agent accuracy.
• check_circle Design, scale, and maintain a high-performance, on-premise RAG service and vector database (e.g., Qdrant, Milvus, Milvus/Chroma) to seamlessly serve internal documentation to our LLMs.
• check_circle Build robust data ingestion and embedding pipelines to ensure internal knowledge bases and documents are updated in real-time for the RAG service.
• check_circle Work tightly with Product, Operations, and the Growth team to ensure alignment.
• check_circle Provide the technical foundation for the Growth team's AI-assisted content creation, verification, and contextual validation pipelines.
• check_circle Build repeatable AI engines that can guarantee linguistic, cultural, and regulatory correctness across dozens of markets simultaneously.
• check_circle A senior AI/MLOps engineer with proven experience scaling self-hosted LLM infrastructure in a production environment.
• check_circle Experienced with semantic search, vector databases, and information retrieval techniques (RAG) at scale.
• check_circle Deeply experienced with Python, PyTorch, CUDA, and modern inference serving frameworks.
• check_circle Experienced in using AI as a production and verification tool, not a gimmick.
• check_circle Comfortable working closely with networking and storage architects to eliminate I/O bottlenecks in a ZFS/Linux ecosystem.
• check_circle Highly structured, data-driven, and execution-focused.
• check_circle Motivated by building systems that scale, not campaigns that win awards.

Benefits

• check_circle A senior tech role with direct ownership over a state-of-the-art AI hardware stack.
• check_circle A fast-scaling international fintech with real infrastructure, licenses, and products.
• check_circle Competitive salary and employment conditions.
• check_circle A modern office in Amsterdam Houthavens overlooking ‘Het IJ’.
• check_circle Daily healthy lunches prepared by our in-house chef.
• check_circle A culture that values execution, ownership, and long-term thinking.

About the company