and scaling multi-agent systems or tool-augmented LLM workflows. Familiarity with secure cloud development practices and IAM role design. Understanding of LLM fine-tuning, embeddings, vector stores (e.g., Pinecone, FAISS, OpenSearch). Exposure to contact centre automation, conversational agents, or RAG pipelines. Adecco is a disability-confident employer. It is important to us that we run an inclusive and More ❯
and scaling multi-agent systems or tool-augmented LLM workflows. · Familiarity with secure cloud development practices and IAM role design. · Understanding of LLM fine-tuning, embeddings, vector stores (e.g., Pinecone, FAISS, OpenSearch). · Exposure to contact centre automation, conversational agents, or RAG pipelines. Please click here to find out more about our Key Information Documents. Please note that the documents More ❯
City of London, London, United Kingdom Hybrid / WFH Options
Anson McCade
varied use cases. Build agentic workflows and reasoning pipelines using frameworks such as LangChain, LangGraph, CrewAI, Autogen, and LangFlow. Implement retrieval-augmented generation (RAG) pipelines using vector databases like Pinecone, FAISS, Chroma, or PostgreSQL. Fine-tune prompts to optimise performance, reliability, and alignment. Design and implement memory modules for short-term and long-term agent behaviours. Deploy models and orchestrate More ❯
varied use cases. Build agentic workflows and reasoning pipelines using frameworks such as LangChain, LangGraph, CrewAI, Autogen, and LangFlow. Implement retrieval-augmented generation (RAG) pipelines using vector databases like Pinecone, FAISS, Chroma, or PostgreSQL. Fine-tune prompts to optimise performance, reliability, and alignment. Design and implement memory modules for short-term and long-term agent behaviours. Deploy models and orchestrate More ❯
Experience building with generative AI applications in production environments. Expertise with microservices architecture and RESTful APIs. Solid understanding of database technologies such as PostgreSQL and vector databases as Elastic, Pinecone, Weaviate, or similar. Familiarity with cloud platforms (AWS, GCP, etc.) and containerized environments (Docker, Kubernetes). You are committed to writing clean, maintainable, and scalable code, following best practices in More ❯
largescale transformer models (BERT, GPT) and promptengineering for sentiment tasks Background building activelearning and annotation pipelines to bootstrap training data Familiarity with semantic search or vector databases (Elasticsearch, FAISS, Pinecone) for topic modeling and similarity queries Familiarity with crypto markets, order books, and risk-management frameworks Familiarity with anomalydetection methods for streaming text and timeseries data Experience developing EVM smart More ❯
London, South East, England, United Kingdom Hybrid / WFH Options
Opus Recruitment Solutions Ltd
and reliability Essential Skills Strong Python skills and experience with Hugging Face Transformers Familiarity with LLM fine-tuning and inference optimisation Experience with vector search and embeddings (e.g. FAISS, Pinecone) Understanding of prompt engineering and few-shot learning Ability to work independently in a hybrid, agile environment Nice to Have Experience with LangChain, LlamaIndex, or similar orchestration tools Exposure to More ❯
prompts for LLMs (OpenAI, Claude, etc.) Building prompt libraries and evaluation frameworks Structuring unstructured data (PDFs, notes, forms) into usable formats Working with RAG pipelines and vector databases (FAISS, Pinecone, etc.) Embedding LLMs into user-facing healthcare tools (e.g., AI assistants, in-context help) Collaborating with product, design, and clinical teams to ship real features What You’ll Bring Experience More ❯
rapid, iterative cycles with weekly releases Prompt Engineering: Able to craft, test, and refine prompts for outputs like chat, image, or video LLM + Vector Tools: Experience with embeddings, Pinecone/Weaviate, and building RAG-style pipelines Why Join Magic Group? No red tape. Just build, launch, and scale A small, senior team with high trust and even higher impact More ❯
prompt tweaks changed an LLM's output to match a specific product need. Nice-to-Haves LangChain, LlamaIndex, or any RAG experiment on your GitHub. Vector database dabbling (pgvector, Pinecone). A side project people outside your family have used. Our Stack React 18 Next.js Node 20 FastAPI OpenAI & Anthropic APIs Postgres + pgvector Vercel Fly.io GitHub Actions Cursor & Windsurf More ❯
controllers. Develop and maintain AI microservices using Docker, Kubernetes, and FastAPI, ensuring smooth model serving and error handling; Vector Search & Retrieval: Implement retrieval-augmented workflows: ingest documents, index embeddings (Pinecone, FAISS, Weaviate), and build similarity search features. Rapid Prototyping: Create interactive AI demos and proofs-of-concept with Streamlit, Gradio, or Next.js for stakeholder feedback; MLOps & Deployment: Implement CI/… experience fine-tuning LLMs via OpenAI, HuggingFace or similar APIs; Strong proficiency in Python; Deep expertise in prompt engineering and tooling like LangChain or LlamaIndex; Proficiency with vector databases (Pinecone, FAISS, Weaviate) and document embedding pipelines; Proven rapid-prototyping skills using Streamlit or equivalent frameworks for UI demos. Familiarity with containerization (Docker) and at least one orchestration/deployment platform More ❯
