15 of 15 Observability Jobs in East London

Prefect, TorchServe, Triton, vLLM, SHAP, LIME, pandas, Spark, SQL LLM tooling: Familiarity with LangChain, Semantic Kernel, prompt chaining, vector search, and context management Performance & observability: Skilled in debugging distributed systems, tuning for latency, and implementing monitoring Platform mindset: Can contribute to shared SDKs and tools, raising engineering velocity ...

LangChain, foundation model platforms, vector databases, structured outputs, tracing and evaluation techniques Experience applying modern engineering practices, including testing, CI/CD, DevOps, observability, secure development, code quality, architecture reviews and production-readiness Experience designing monitoring approaches, dashboards or evaluation mechanisms to understand the performance and behaviour of AI-enabled ...

enable repeatable releases Develop reusable engineering assets (libraries, templates, reference architectures, infrastructure-as-code patterns) to reduce technical debt and accelerate delivery Implement observability for AI services (logging/metrics/tracing), model performance monitoring, and quality/drift checks with actionable alerting Partner with data scientists, data engineers, platform ...

shape architectures to meet these demands. Lead technical delivery across solution threads: set technical direction, mentor engineers, and ensure systems are production‐ready (reliability, observability, security, runbooks). Continue your development through the Applied AI Engineering Academy focused on advanced patterns and engineering leadership. EY Grade: Manager (UK) What ...

with other teams to agree clear interfaces and understand how changes affect the wider payment journey. Improve the systems you operate. Strengthen testing and observability, diagnose production issues, and use what you learn to make services more dependable. Help the team succeed. Contribute across workstreams, share domain knowledge and help ...

Agents: Develop the infrastructure required to run increasingly agent-driven AI workflows reliably in production, including state management, task execution, model routing, retries and observability Support AI Infrastructure: Work closely with our AI engineers supporting production NLP, LLM and quantitative model workloads, including our in-house GPU infrastructure. Automate Infrastructure … Build and manage Infrastructure-as-Code using Pulumi and automate deployments through GitHub Actions. Own Reliability & Observability: Build monitoring, logging, tracing and alerting across our data, model, service and agent infrastructure. Requirements Build the data foundations behind twice award-winning market intelligence. At Permutable, we turn global reporting into structured ...

office twice a month for team collaboration and meetings. About you: You are an experienced Machine Learning Engineer who prioritises system reliability, latency and observability as much as model accuracy You have strong Python skills and experience of leveraging the AWS stack to move models from development environments to robust ...

performant infrastructure that underpins critical public-sector services. Youll combine your background in AWS, DevOps, cloud engineering, and automation with a focus on reliability, observability, and scalability. Youll also work with event driven technologies, identity and access management, and data platforms, ensuring their orchestration solutions are resilient, secure, and future … PostgreSQL, Elasticsearch, and MongoDB Configure and support identity and access management (IdAM) solutions such as Keycloak Monitor system health, performance, and capacity using modern observability stacks (Prometheus, Grafana, ELK, OpenTelemetry) Champion DevSecOps practices, embedding security and compliance into every stage of delivery Automate deployment, scaling, and recovery processes to improve ...

performant infrastructure that underpins critical public-sector services. Youll combine your background in AWS, DevOps, cloud engineering, and automation with a focus on reliability, observability, and scalability. Youll also work with event driven technologies, identity and access management, and data platforms, ensuring their orchestration solutions are resilient, secure, and future … PostgreSQL, Elasticsearch, and MongoDB Configure and support identity and access management (IdAM) solutions such as Keycloak Monitor system health, performance, and capacity using modern observability stacks (Prometheus, Grafana, ELK, OpenTelemetry) Champion DevSecOps practices, embedding security and compliance into every stage of delivery Automate deployment, scaling, and recovery processes to improve ...

microservices setup. You’ll work with product managers and partner banks to enable international payments and liquidity management. You’ll lead technical decisions, improve observability and testing, and mentor engineers while solving complex problems end-to-end in production. #J-18808-Ljbffr ...

that align with governance and risk requirements. You will collaborate with data scientists, platform teams, and stakeholders to ensure end-to-end delivery, implement observability, and uplift team capability through coaching and standards #J-18808-Ljbffr ...

backend team. You will collaborate on integrations with EveryMatrix and other vendor APIs, shape caching, data stores, and real-time event flows, and ensure observability with SLOs and incident leadership. #J-18808-Ljbffr ...

About Scale Factory We are an AI enablement consultancy. Delivering quality-led AI-first foundations, embedding capability and excellence into the foundational fabric of the companies we work with. We give leaders the confidence to ...

Engineers, fostering a culture of ownership, collaboration and continuous improvement. Define and drive the strategy for AWS, cloud infrastructure and DevOps. Champion reliability, security, observability and operational excellence across the engineering function. Embed “You Build It, You Run It” principles, empowering engineering teams to take ownership of their services throughout … experience in cloud infrastructure, with strong AWS knowledge. DevOps and automation: Experience with CI/CD pipelines and Infrastructure as Code. Reliability and observability: A solid understanding of monitoring, observability and incident management. Containers and security: Knowledge of Docker and cloud security best practices. Technical and strategic leadership: The ability ...

engineering standards, best practices and reusable patterns while partnering with Enterprise Architecture and influencing technical direction Drive engineering excellence by improving code quality, testing, observability, reliability and operational practices Support end-to-end delivery by guiding teams through complex technical challenges, improving decision-making, and contributing to planning and risk … data lakes/lakehouse architectures, Iceberg or similar table formats, as well as batch and streaming processing Knowledge of data quality, governance, cataloguing and observability tools (e.g. Datadog), with DBT or AI-assisted engineering practices as a plus ...