2 of 2 Memory Management Jobs in Liverpool

Rapidly build and iterate on LLM- and agent-based prototypes for various use cases, including chatbots, copilots, and A2A task agents. Implement agentic workflows, multi-step reasoning pipelines, and memory management using frameworks such as LangChain, CrewAI, and Autogen. Engineer and tune prompts to enhance the performance and reliability of generative tasks. Design RAG systems using vector databases … grounded LLM responses. Utilize Guardrails to implement applications that adhere to responsible AI guidelines. Optimize model performance for latency, throughput, and cost-efficiency. Implement short-term and long-term memory modules to support persistent agent behaviours. Use cloud platforms such as Amazon Bedrock, Google Vertex AI, and Azure AI Studio for model orchestration and deployment. Build and integrate UI More ❯

innovation-driven role focused on rapidly prototyping advanced AI systems using LLMs, autonomous agents, and semantic search. The engineer will work across the full stack-from prompt engineering and memory management to UI and cloud deployment-using tools like LangChain, CrewAI, and vector databases. Core Responsibilities Build and iterate on LLM/agent-based prototypes (e.g., copilots, chatbots … A2A agents). Implement multi-step reasoning, memory modules, and RAG pipelines. Use frameworks like LangChain, LangGraph, CrewAI, and tools like Pinecone, FAISS. Optimize performance and ensure responsible AI practices. Deploy via cloud platforms (AWS Bedrock, Azure AI, Google Vertex). Build UIs (Streamlit, Gradio, React) and integrate APIs and databases. Preferred Skills Experience with multi-agent systems and More ❯