AI Platform Engineer - LLM Infrastructure,April 13, 2026### Job DescriptionLocation: London, UK Work Model: On-site Role Type: Full-TimeWe are looking for an AI Platform Engineer with strong experience in LLM infrastructure and scalable AI systems to join our client’s on-site team in London.This role focuses on building and maintaining internal platforms that power Generative AI applications, enabling scalable model deployment, inference, and experimentation.—### What You’ll Do* Build and maintain infrastructure for LLM deployment and inference* Develop scalable systems for embeddings, vector search, and RAG pipelines* Design APIs and services for AI model consumption* Optimise performance, latency, and cost of AI workloads* Collaborate with AI engineers and data scientists to productionise models* Implement monitoring and observability for AI systems* Support experimentation and model lifecycle management—### What We’re Looking For#### **Required Skills &

Experience* Strong experience with cloud platforms such as Amazon Web Services, Google Cloud, or Microsoft Azure* Experience with containerisation using Docker and orchestration via Kubernetes* Experience working with LLMs, embeddings, and vector databases* Strong programming skills (Python preferred)* Experience designing scalable backend systems—#### **Nice to Have* Experience with RAG architectures and GenAI frameworks* Familiarity with model serving frameworks and inference optimisation* Knowledge of MLOps workflows—Location: London, UK Work Model: On-site Role Type: Full-TimeLocation,Experience levelMid-Senior level## Work Location

Experience* Strong experience with cloud platforms such as Amazon Web Services, Google Cloud, or Microsoft Azure* Experience with containerisation using Docker and orchestration via Kubernetes* Experience working with LLMs, embeddings, and vector databases* Strong programming skills (Python preferred)* Experience designing scalable backend systems—#### **Nice to Have* Experience with RAG architectures and GenAI frameworks* Familiarity with model serving frameworks and inference optimisation* Knowledge of MLOps workflows—Location: London, UK Work Model: On-site Role Type: Full-TimeLocation,Experience levelMid-Senior level## Work Location #J-18808-Ljbffr