3 of 3 Model Context Protocol Jobs in the City of London

inference pipelines using PyTorch, and related ML frameworks Source, curate, and prepare training datasets; implement preprocessing, augmentation, and validation workflows. Run structured experiments, evaluate model performance, and iterate based on measurable results Build, deploy, and operate end-to-end MLOps pipelines, including experiment tracking, model versioning, and production … deploy agent-based AI systems that can execute multi-step workflows and integrate with external tools. Build Model Context Protocol (MCP) Servers to enable standardised integration between models, APIs, and data sources. Evaluate and integrate large language models into production systems where they add clear value. Collaborate ...

robust evaluation and monitoring frameworks, including online and offline testing, A/B experiments and performance dashboards. • Integrate AI agent functionality with applications through MCP servers and reliable tool configurations. • Develop secure and scalable RAG pipelines, including ingestion, text processing, metadata handling and vector search in GCP. • Embed security, compliance … testing. • Hands‐on experience working with LLMs, embeddings, prompt engineering, tool calling and RAG design. • Practical knowledge of GCP services including Vertex AI, Model Garden, BigQuery, Cloud Run and Google’s ADK. • Experience with document and data processing using tools such as Apache Tika, plus storage or caching technologies ...

using Python Hands-on Experience with API Development and Microservices architecture and End to End integrations Knowledge of RAG (Retrieval-Augmented Generation ) and ADK, MCP Solid understanding of LLMs, prompt engineering, and graph-based workflows. Hands-on Experience with API Development and Microservices architecture Experience in CI/CD pipelines … containerization (Docker/Kubernetes)., Harness and Git actions. Practical experience implementing LLM and GenAI solutions, including prompt engineering, model fine‐tuning, RAG pipelines, embeddings, and vector databases. ...