5 of 5 Observability Jobs in Edinburgh

reliability, scalability, and performance of the core platform. You will guide architectural direction, lead complex infrastructure initiatives, and drive improvements across deployment pipelines, observability, and systems design. This role includes contributing hands-on code, serving as the technical escalation point, and partnering with internal teams and external vendors to ensure ...

with GPU cluster management (CUDA, NCCL, Triton Inference Server) and performance tuning across accelerators. Solid grasp of cloud-native orchestration (Docker, Kubernetes, Helm) and observability tooling (Prometheus, Grafana, Jaeger). Proven ability to translate cutting-edge research into engineered solutions that can scale globally. Why this role stands out Influence ...

engineering projects A range of data stores including MySQL, Cassandra, Redis and BigQuery RabbitMQ for queues Internal services communication with both and gRPC An observability stack that counts on GrafanaLab, Loki, Tempo, Looker, and more Cloud environments - Google Cloud Platform Experience with Docker and/or Kubernetes is a bonus ...

shape the AI roadmap Mentor engineers across squads and raise engineering standards Build and optimise distributed, API first systems powering AI workflows Drive observability, testing, operational excellence and cost optimisation Prototype new AI powered features to enhance user experience What success looks like Consistently delivering technically strong, user focused … with GraphRAG or knowledge graph based approaches Strong grounding in LLM architectures, fine tuning and agentic workflows MLOps experience covering deployment, versioning and monitoring Observability experience for distributed AI systems Data ingestion experience for vector and graph stores CI/CD automation for both software and ML pipelines Full stack ...

management, upgrades, patching (including air-gapped environments). Support future evolution into virtualised clusters via the OpenStack CAPI provider. Integrate with OSS APIs and observability platforms. Ensure clusters meet TSA and CIS hardening requirements. The Person Strong Kubernetes experience (RKE2 preferred), Rancher, GitOps. Proven experience with CAPI and Metal3. Security … hardening: TSA, CIS benchmark. Experience integrating with OSS and observability tooling. For immediate consideration please apply online and contact Dominik Bart at Franklin Fitch ...