13 of 13 Retrieval-Augmented Generation Jobs in Edinburgh

architecture strategy and roadmap. Build scalable AI/ML and Agentic AI platforms spanning LLMs, retrieval-augmented generation (RAG), embeddings and semantic search. Lead on deployment, governance and integration patterns, advise clients on platform capability and implementation strategy, and partner with engineering, data, DevOps … business teams to deliver end-to-end solutions. Tech environmentPython, LLMs (prompt engineering, fine-tuning, RAG), LangChain/LangGraph, agent frameworks, vector databases, MLOps/LLMOps, AWS, Azure, GCP, Databricks, Kubernetes and GPU infrastructure. What we're looking forProven enterprise AI or ML architecture design, strong cloud and modern data ...

multi‐modal large language models across text, image, audio, and video Design and implement agentic workflows using prompt engineering, Retrieval‐Augmented Generation (RAG), APIs, and enterprise data integrations Fine‐tune, optimize, and deploy large language and multi‐modal models with a focus on scalability … within agile delivery environments Bonus Points For Experience building AI agent frameworks or autonomous orchestration platforms Knowledge of vector databases, semantic search, and advanced RAG architectures Experience with cloud platforms such as AWS, Azure, or GCP for AI workloads Familiarity with financial services, banking, or regulated enterprise environments Exposure ...

Practical experience implementing components of data pipelines, including real-time streaming tools (AWS Kinesis, Kafka), data orchestration (dbt, Airflow), and managing vector databases for RAG architectures. Observability & Cost Management: SRE/Platform experience with the practical application of real-time monitoring and cloud cost optimisation using native CSP tools ...

infrastructure required to run AI workloads reliably, moving client architectures from static data lakes to dynamic Vector Databases and Retrieval‐Augmented Generation (RAG) architectures. Agentic Development: Build production‐grade Agentic Workflows and custom AI agents, utilising advanced toolsets to bridge the widening market implementation … maintaining data orchestration toolsets (e.g., dbt, Apache Airflow), ETL/ELT methodologies, real‐time streaming (e.g., AWS Kinesis, Apache Kafka), Vector databases, and RAG architectures. Observability & FinOps: Experience implementing modern observability tooling (OpenTelemetry) alongside automated cost‐control systems (such as Karpenter, Infracost, OpenCost, or Cloud Custodian). Domain & Sector Experience ...

Snowflake Platform including Cortex, Horizon and Snowpark. Advanced proficiency in Azure, AWS, or GCP platform setup and administration. Practical understanding of Generative AI, RAG frameworks, Agentic AI architectural patterns, and security guardrails. Solid understanding of data governance standards (lineage, access control) and performance/cost optimization frameworks. Job responsibilities Lead ...

scale in production environments and create capacity for our business partners. From AI-powered investment insights and risk management solutions to next-generation agentic workflows - our work is helping to shape the future of BlackRock. Our teams work on some of the firm's highest priority strategic initiatives … standards such as Model Context Protocol (MCP) for connecting agents to tools and data. Experience with retrieval systems for agents: retrieval-augmented generation, embedding models, vector databases, and long-term memory. Experience with machine learning libraries (e.g. PyTorch, Tensorflow), cloud platforms ...

prototypes, products and production ready solutions Designing and implementing end to end AI solutions that integrate with enterprise systems Working with LLMs, prompt engineering, RAG patterns, embeddings and fine tuning Developing AI agents and agentic workflows using modern frameworks Working with vector databases, APIs and modern data platforms Supporting … collaborative, high performing environment Experience Required: Strong Python and SQL experience Applied AI engineering, ML engineering or software engineering background Experience with LLMs, RAG, embeddings, prompt engineering or fine tuning Exposure to LangChain, LangGraph, Agent Development Kit or similar agent frameworks Experience with vector databases such as Pinecone, Chroma ...

Experience designing and operating APIs, microservices, distributed systems, and event-driven architectures at enterprise scale. Exposure to Generative AI, large language models, retrieval-augmented generation, semantic search, embeddings, knowledge retrieval, or agentic workflow patterns. Strong focus on software quality, including automated testing ...

efficiency ; shorter cycle times, less manual effort, higher accuracy, lower cost-to-serve. Engineer the agent core: apply prompt engineering, context engineering, prompt caching, RAG/context-graph retrieval, memory, tool/function calling, MCP integration and multi-agent orchestration. Integrate to standards: connect agents into client ecosystems … Agents SDK, AWS Bedrock AgentCore or Microsoft Agent Framework/Semantic Kernel). Solid command of agent engineering: prompt engineering, context engineering, prompt caching, RAG/context graphs, tool/function calling, MCP, and multi-agent orchestration. Eval-driven development: designing evaluation harnesses and measuring agent quality, safety and reliability. ...

advisor to client CxOs. Key Responsibilities Architecture and Solution Design: Architect enterprise AI solutions using frontier models (Claude, GPT, Gemini family) across agentic automation, RAG, copilots, and multi-modal applications. Pre-Sales and Discovery: Lead technical solutioning during pre-sales and discovery, translating client business challenges into scalable AI architectures … specifically on applied AI/ML or Generative AI. Hands-on GenAI Depth: Proven experience architecting solutions with frontier modelsincluding prompt engineering, fine-tuning, RAG, and agentic/multi-agent system design. LLMOps/MLOps Grounding: Expertise in evaluation frameworks, observability, cost and latency optimization, guardrails, and safe deployment ...

Strands Agents Build, integrate, and maintain MCP (Model Context Protocol) servers that expose capabilities to AI agents across client platforms Architect and implement RAG pipelines using Amazon Bedrock Knowledge Bases, managing vector stores, embeddings, and document ingestion from S3 and other sources Apply the A2A (Agent-to-Agent) protocol … integrated MCP servers in a production or near-production context Strands Agents — familiarity with the framework and its application to agentic workflows on AWS RAG implementation — knowledge base design, chunking strategy, vector store configuration, and retrieval evaluation Python — strong, applied proficiency in an AWS and AI context ...

capabilities across all of these services. With our thought leadership and culture of innovation, we apply industry expertise, diverse skill sets and next-generation technology to each business challenge. We believe in inclusion and diversity and supporting the whole person. Our core values comprise of Stewardship, Best People … Azure ML, OpenAI, Langchain, AutoML, OCR, STT, feature stores, vector DBAI/ML architectural patterns and best practices e.g. data drift detection, experimentation tracking, RAG, deployment modelsCloud infrastructure (networking, security, storage, monitoring, scaling, DR/HA) on one or more cloud platformsSW Engineering and DevSecOpsSet yourself apart: Certified cloud Machine ...

capabilities across all of these services. With our thought leadership and culture of innovation, we apply industry expertise, diverse skill sets and next-generation technology to each business challenge. We believe in inclusion and diversity and supporting the whole person. Our core values comprise of Stewardship, Best People … OpenAI, Langchain, AutoML, OCR, STT, feature stores, vector DB AI/ML architectural patterns and best practices e.g. data drift detection, experimentation tracking, RAG, deployment models Cloud infrastructure (networking, security, storage, monitoring, scaling, DR/HA) on one or more cloud platforms SW Engineering and DevSecOps Set yourself apart: Certified ...