601 to 625 of 2,456 Remote/Hybrid Observability Jobs

services . Work with self-hosted inference and model-serving technologies where appropriate, including tools such as vLLM, SGLang and Ollama . Design evaluation, observability and monitoring frameworks to assess model performance, system health, reliability and business impact. Optimise AI solutions for performance, scalability, security and cost-efficiency. Identify where ...

deployment strategies Understanding of infrastructure as code (e.g. OpenTofu) and environment management concepts Experience with cloud-native SaaS architectures (preferably Azure) Familiarity with observability, monitoring, and release health metrics Ability to work hands-on with engineering teams to diagnose and improve delivery pipelines Understanding of modern DevOps practices and principles ...

with a cloud provider (AWS/Azure/GCE), or sysadmin/SRE experience in data centers Experience designing, building, and operating high-scale observability or infrastructure systems Working knowledge of networking fundamentals, experience with CNIs or cloud networking infrastructure preferred What We Require 4+ years of professional software development ...

reviews and ensure adherence to engineering standards. Establish best practices for: Clean code and maintainability; Testing strategy (unit, integration, E2E); CI/CD pipelines; Observability and monitoring; Security and performance optimisation. Ensure scalability, reliability, and long‐term technical sustainability of a high‐throughput, event‐driven platform. Reduce technical debt through ...

product organisations or customer-facing digital platformsExperience with onboarding, KYC, or regulated financial services journeysAWS certification (Cloud Practitioner or Associate level)Familiarity with observability and monitoring toolSpecial FactorsVanguard is not offering visa sponsorship for this positionThis is a hybrid position and would require you to work in the office ...

cross-functional partnerships. What We're Looking For Strong production engineering experience: Built, deployed, and operated complex systems in production with emphasis on observability, reliability, performance, and scale. Hands-on LLM/ML systems experience: Production experience with LLMs, fine-tuning, inference pipelines, latency/cost optimization, or evaluation; familiarity ...

applications, including real-time streaming with high volume and concurrent workloads. Presenting designs to technical reviewers, contributing to reviewing designs/code Improving reliability, observability, and performance; Supporting production releases to help team meet SLAs. The role is within BGMs In-Business technology group in London. We are a community ...

Chronicle, or LBM. An understanding of replicated state machines, event sourcing, or deterministic systems. Exposure to cloud environments (AWS/GCP), containers, Kubernetes, or observability tooling. YOU WILL: Design, build, and optimise low-latency Java services and protocols for an Exchange Accelerator product across the delivery lifecycle. Define order, session ...

joiner/mover/leaver Self-hosting and operating shared internal tooling that other teams depend on - deploy, upgrade, back up, own the uptime Observability and alerting design, plus on-call for a distributed team Cloud cost management/FinOps fundamentals Azure is a nice-to-have extension ...

grade deployment pipelines for releasing new models to millions of users reliably Contributing to new inference features Supporting inference for new model architectures Analyzing observability data to tune performance based on real-world production workloads Managing multi-region deployments and geographic routing for global customers Deadline to apply: None. Applications ...

delivery, DevOps, MLOps, and LLMOps practices to enterprise AI programmes. Strong cloud architecture experience across Azure, AWS, or GCP. Experience in model deployment, monitoring, observability, governance, versioning, and operational support. Excellent stakeholder management skills with proven experience engaging clients and senior business leaders. Strong understanding of enterprise security, risk management ...

where it matters: reference implementations, spikes, thorny pipelines, infrastructure-as-code Set engineering standards for the practice testing, CI/CD, environments, code review, observability Coach and unblock engineers; raise the standard of the people around you Practice building and pre-sales Spot and qualify follow-on work inside live ...

where it matters: reference implementations, spikes, thorny pipelines, infrastructure-as-code Set engineering standards for the practice — testing, CI/CD, environments, code review, observability Coach and unblock engineers; raise the standard of the people around you Practice building and pre-sales Spot and qualify follow-on work inside live ...

producing quality output within agreed timelines* **Tooling Familiarity:** Working knowledge of standard engineering tools including Git, Jira, Jenkins, Docker, Hardhat/Foundry, and relevant observability platforms**Development Value**As a Blockchain Software Developer on the Citi Integrated Digital Assets Platform, you will:* Gain **hands-on experience** building production-grade blockchain ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...

optimisation and high-throughput messaging Market-data and reference-data pipelines across multiple asset classes FIX protocol integrations with global banks and liquidity providers Observability and monitoring — dashboards, alerting, and metrics that make system behaviour visible Production systems that handle real money — reliability is not optional What We Need Technical ...