9 of 9 Observability Jobs in Essex

lifecycle tools, model monitoring, and versioning Exposure to tools like KServe, Ray Serve, Triton, or vLLM a big plus Bonus Points: Experience with observability frameworks like Prometheus or OpenTelemetry Knowledge of ML libraries: TensorFlow, PyTorch, HuggingFace Exposure to Azure or GCP Passion for financial services Requirements: Degree in Computer Science ...

functionally with frontend engineers (React) to deliver seamless end-to-end functionality and an exceptional client experience. Own system reliability in production — implementing monitoring, observability, testing frameworks, and proactive performance optimisation. Identify bottlenecks, technical debt, and architectural risks early, and take initiative to design pragmatic, scalable solutions. Champion engineering best ...

performance optimisation for rendering large datasets in the browser. Familiarity with SRE-style practices : SLIs/SLOs, capacity planning, incident response Experience with observability tooling (metrics, tracing, logging) How we work Pragmatic, production-oriented engineering Strong preference for incremental improvement over large rewrites Decisions driven by data: latency, throughput, error ...

/CD (Azure), and post-release monitoring. Work on distributed and asynchronous systems using message queues, background workers, and event-driven workflows. Use observability signals (logging, metrics, tracing, tools like Sentry) to proactively detect, diagnose, and prevent production issues. Collaborate closely with frontend, product, and customer-facing teams to deliver ...

with React Solid understanding of cloud-native engineering on AWS Experience with microservices, messaging patterns and distributed systems A commitment to clean code, testing, observability and operational excellence A proactive and motivated mindset — someone who wants to build, ship and iterate quickly Interest in AI-powered products and a drive ...

including production support Working with data-heavy systems where correctness and reliability matter Integrating with third-party APIs and external systems Improving performance, observability, and resilience Contributing to system design and architectural decisions Helping set and uphold engineering best practices, and acting as a senior presence in the team What ...

using LLMs and GenAI technologies, including prompt engineering, model integration, RAG patterns, agentic workflows, and guardrails. Ability to define and measure quality, accuracy, and observability metrics for GenAI features in production. • Machine Learning & Data Science Knowledge: Solid understanding of machine learning concepts, model deployment, and inference APIs. Ability to evaluate ...

grounding, and context validation. Integrate real-time voice interfaces (STT/TTS, WebRTC, LiveKit) into intelligent conversational flows. Instrument and evaluate system performance using observability and model-faithfulness metrics. What we're looking for Proven ability to build and ship agentic or multi-agent frameworks into production. Expert Python, FastAPI ...

APIs or device level integrations • Experience with mobile CI and CD tools such as Fastlane, GitHub Actions, or Bitrise • Exposure to crash monitoring and observability tooling such as Sentry or Firebase • Experience scaling mobile products across international markets Location and Package • Remote first within the UK with occasional travel ...