5 of 5 Permanent LangSmith Jobs in the UK excluding London

tool use and multi-step reasoning Experience fine-tuning or adapting LLMs for domain-specific use cases Familiarity with LLM evaluation frameworks (e.g. RAGAS, LangSmith) Knowledge of LLM security, hallucination mitigation and responsible AI practices Masters degree in AI, Machine Learning, Data Science or a related field ...

knowledge systems: Practical experience designing and building retrieval-augmented generation pipelines AI evals and observability: Experience building evaluation frameworks and using tools such as LangSmith to monitor and constrain agent behaviour in production LLMOps: Familiarity with the operational practices for deploying, monitoring, and maintaining LLMs in production environments Data science ...

Microservices, FastAPI. Cloud & DevOps: AWS/Azure, Docker, Kubernetes, Terraform, CI/CD. Data & Vector Search: PostgreSQL, MongoDB, Pinecone, Qdrant, ChromaDB, PGVector. Observability & Tooling: LangSmith, Langfuse, Git, GitHub, GitLab. Your Role: Collaborate with the team to develop GenAI proof-of-concepts (POCs) for clients using technologies like Retrieval-Augmented Generation … experience with Docker, Kubernetes, and Docker Compose. Infrastructure as Code (IaC): Exposure to tools like Terraform. Monitoring Tools: Familiarity with LLM monitoring tools like Langsmith, Langfuse, or similar. CI/CD: Experience with continuous integration and deployment tools such as GitLab, GitHub, or Jenkins. Vector Databases: Experience with ...

fine-tuning experience Familiarity with real-time streaming, multimodal models, or search technologies such as Elasticsearch Experience with model observability tools such as LangSmith or Weights & Biases Background in a regulated or specialised vertical (financial services, healthcare, energy, legal, retail), with an understanding of compliance, security, and responsible AI considerations ...

LangChain agent sub-graphs and multi-step workflows. LLM Integration : Improve prompt engineering, orchestrate multiple models, and implement tool-calling logic. System Observability : Use LangSmith or equivalent tracing/logging to monitor agent behaviour and performance. Benchmarking & Evaluation : Contribute to LLM benchmarking across tasks and model families. API Engineering : Build ...