15 of 15 Langfuse Jobs in the UK

Chroma, pgvector, FAISS; embeddings, semantic and hybrid search, reranking MLOps/LLMOps & deployment: Docker, Kubernetes, FastAPI, CI/CD; observability, tracing, evaluation tooling (LangSmith, LangFuse); guardrails, prompt/version management Responsible AI & safety: bias & fairness, hallucination mitigation, evaluation, privacy, security, governance of AI and agentic systems Solution Design : Ability ...

production. AI Operations & Observability Experience implementing monitoring, tracing, evaluation, and cost optimisation for AI systems. Experience with observability solutions such as Arize Phoenix, Langfuse, or Langsmith. Understand the operational challenges of deploying LLM‐powered applications, including latency, reliability, hallucination monitoring, and model quality evaluation. Collaboration & Technical Leadership Enjoy collaborating across ...

GraphRAG and agentic RAG. LLMOps, Evaluation & Responsible AI – operationalizing LLM and agentic systems at scale; evaluation harnesses, quality metrics, observability, tracing and monitoring (LangSmith, LangFuse); guardrails, red‐teaming and continuous optimization of accuracy, cost and latency. Understanding of AI governance, security, privacy, bias/fairness and emerging regulations. Machine Learning ...

governance, data privacy, and regulatory frameworks Support pre‐sales activities through technical solutioning, demos, and PoC development Apply observability and monitoring using tools like Langfuse, Arize, and OpenTelemetry Contribute to architecture decisions and technical standards across engagements Requirements 6+ years in AI/ML engineering, data science, or applied ...

with high-traffic, real-time consumer platforms Fine-tuning experience and the judgement to know when it beats prompting or RAG Observability tooling (LangSmith, Langfuse, W&B) and cost optimisation Experience with AI coding tools (Claude Code, Codex, Copilot) What's on Offer Competitive salary benchmarked to your level ...

evaluation layer — golden datasets, regression suites, agent-level metrics and human review workflows for non-deterministic outputs. Own the observability and tracing stack (Langfuse, CloudWatch) and the runtime quality, latency and cost envelope of the platform. Team leadership and capability build Lead the in-house agentic engineering team (Agent Developer ...

Tech Stack: Backend Python FastAPI Agent Development Kit (ADK) Datastores PostgreSQL BigQuery Firestore Infrastructure Google Cloud Platform (GCP) RabbitMQ Terraform Monitoring & Observability Grafana Prometheus Langfuse incident.io Sentry What to Expect from Our Hiring Process At Plum, we value a lot the time you devote to the hiring process, this ...

wider Google Cloud Platform (e.g. Cloud Run, Pub/Sub, Cloud Storage). Experience with an LLM observability or evaluation platform such as Langfuse, LangSmith, Braintrust or Arize Phoenix. Understanding of MCP and integration of tools with agentic systems. Experience grounding LLM output in data via techniques such ...

communication skills with the ability to work across multidisciplinary teams Nice to Have * Public sector or GDS experience * Experience with LLMobservability tools such as Langfuse * Cloud and infrastructure experience including AWS, Terraform and GitHub * Startup or entrepreneurial background * Experience working within multidisciplinary Agile teams Summary Forward Deploy Engineer required ...

plus. Previous experience building AI agents, conversational interfaces, Slack integrations, or developer-focused tools is advantageous. Familiarity with evaluation and observability frameworks such as Langfuse or LangChain is a plus. Knowledge of subscription business models, mobile applications, app stores, or developer platforms is beneficial. Contributions to open-source ...

Engineer to advance cutting-edge AI capabilities across our global financial markets infrastructure. You will work with Azure AI Foundry, Azure AI Search and Langfuse to design scalable agents, evaluate performance, and optimize costs while collaborating with teams worldwide. Join us to shape multi-agent workflows, implement guardrails, and contribute ...

optimize multi-agent AI solutions, focusing on scalable deployment and cost-efficient performance. Responsibilities include designing AI systems with LangChain/LangGraph, implementing Langfuse-driven experiments, and integrating Azure AI services. Strong collaboration across teams to deliver robust AI capabilities is essential. #J-18808-Ljbffr ...

Enterprise Architect — Artificial Intelligence AI/ML Infrastructure, Platform & Governance Role Summary World Wide Technology is looking for a deeply technical Enterprise Architect who will own the delivery of AI projects end to end from ...

Management (APIM), particularly the secure exposure and management of large language models (LLMs). Azure observability, including Azure Monitor, Application Insights, and Azure Workbooks. Langfuse, including designing and conducting evaluations and assessing outcome quality and value relative to token usage and cost. Datadog for logging, observability, and LLM analytics. … agent harnesses and APIM, and its ingestion into Langfuse. Developing experimental agents using Azure AI Foundry Agent Service and Azure AI SDKs. Advanced Langfuse usage, including datasets, experiments, prompt management, custom evaluators, tracing, and cost analysis. Experimenting with advanced RAG techniques such as hybrid search, semantic ranking, query rewriting, reranking ...

Management (APIM), particularly the secure exposure and management of large language models (LLMs). Azure observability, including Azure Monitor, Application Insights, and Azure Workbooks. Langfuse, including designing and conducting evaluations and assessing outcome quality and value relative to token usage and cost. Datadog for logging, observability, and LLM analytics. … agent harnesses and APIM, and its ingestion into Langfuse. Developing experimental agents using Azure AI Foundry Agent Service and Azure AI SDKs. Advanced Langfuse usage, including datasets, experiments, prompt management, custom evaluators, tracing, and cost analysis. Experimenting with advanced RAG techniques such as hybrid search, semantic ranking, query rewriting, reranking ...