client are a top tier consultancy looking for x2 AI Engineers on a 6 months contract. Key Responsibilities: Design and build AI workflows using LangChain and LLMs (eg, OpenAI, Claude, Mistral, etc.) Develop Python-based services and APIs for integration with AI models Implement Retrieval-Augmented Generation (RAG) pipelines using vector databases (eg, FAISS, Weaviate) Collaborate with data scientists … or Machine Learning Engineer Strong Python development skills Hands-on experience with LangChain and other LLM frameworks Familiarity with vector databases (eg, FAISS, Pinecone, Weaviate) Experience working with OpenAI, Anthropic, or other generative AI APIs Ability to work independently in a remote team and deliver results to tight timelines Desirable Skills: Knowledge of cloud platforms (AWS/GCP/ More ❯
into existing platforms, you'll be at the forefront of transforming ideas into intelligent, scalable solutions.?? What You’ll Be Doing Designing, testing, and refining 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 … tools (e.g., AI assistants, in-context help) Collaborating with product, design, and clinical teams to ship real features What You’ll Bring Experience with LLMs and prompt engineering (OpenAI, Anthropic, etc.) Familiarity with structured (SQL, JSON, CSV) and unstructured data Exposure to vector stores and retrieval-augmented generation (RAG) Strong Python skills and comfort working with APIs and data More ❯
into existing platforms, you'll be at the forefront of transforming ideas into intelligent, scalable solutions. What You'll Be Doing Designing, testing, and refining 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 … tools (eg, AI assistants, in-context help) Collaborating with product, design, and clinical teams to ship real features What You'll Bring Experience with LLMs and prompt engineering (OpenAI, Anthropic, etc.) Familiarity with structured (SQL, JSON, CSV) and unstructured data Exposure to vector stores and retrieval-augmented generation (RAG) Strong Python skills and comfort working with APIs and data More ❯
