pipelines over structured and unstructured health data (EHRs, patient notes, device logs, clinical documentation). Develop indexing strategies using vector databases (e.g., FAISS, Weaviate, Pinecone) and embedding models (e.g., BioBERT, ClinicalBERT). Integrate RAG outputs into user-facing applications, ensuring responses are grounded, reliable, and privacy-compliant. Work closely with More ❯
pipelines over structured and unstructured health data (EHRs, patient notes, device logs, clinical documentation). Develop indexing strategies using vector databases (e.g., FAISS, Weaviate, Pinecone) and embedding models (e.g., BioBERT, ClinicalBERT). Integrate RAG outputs into user-facing applications, ensuring responses are grounded, reliable, and privacy-compliant. Work closely with More ❯
problem-solving skills and ability to work in a fast-paced, agile environment. Nice-to-Have Skills: Hands-on experience with Vector Databases (FAISS, Pinecone, Weaviate, PGVector, etc.). Experience fine-tuning LLMs for domain-specific applications. Knowledge of data privacy, governance, and compliance in AI-driven systems. Previous work More ❯
and improving developer workflows. Excellent communication and collaboration skills in a remote-first environment. Experience contributing to open-source AI projects. Experience with LangChain, Pinecone, or similar AI frameworks/infrastructure. Past experience building AI features into developer platforms or tools. Benefits Our entire company is distributed, so we take More ❯
Develop and optimise RAG pipelines using LangChain, LlamaIndex, or Haystack. Build ingestion workflows (OCR, chunking, embedding, semantic search) and integrate with vector databases (FAISS, Pinecone, Qdrant). Ensure seamless integration of GenAI services into business workflows, prioritising security, scalability, and compliance. Collaborate with cross-functional teams (data scientists, architects, engineers More ❯
london, south east england, United Kingdom Hybrid / WFH Options
twentyAI
Develop and optimise RAG pipelines using LangChain, LlamaIndex, or Haystack. Build ingestion workflows (OCR, chunking, embedding, semantic search) and integrate with vector databases (FAISS, Pinecone, Qdrant). Ensure seamless integration of GenAI services into business workflows, prioritising security, scalability, and compliance. Collaborate with cross-functional teams (data scientists, architects, engineers More ❯
others for prompt and model optimisations. Comfortable working with databases (relational & vector), and large-scale data sets and pipelines (e.g. AWS Glue, Redshift, RDS, Pinecone, Opensearch). Hands-on experience with AI Cloud Infrastructure for MLOps (e.g. Google Vertex AI/AWS Bedrock), including deploying AI applications and managing AI More ❯
others for prompt and model optimisations. Comfortable working with databases (relational & vector), and large-scale data sets and pipelines (e.g. AWS Glue, Redshift, RDS, Pinecone, Opensearch). Hands-on experience with AI Cloud Infrastructure for MLOps (e.g.Google Vertex AI/AWS Bedrock), including deploying AI applications and managing AI cloud More ❯