TechOps-CloudOps-AI-ML Platform Operations Senior Engineer
EY
EY
Join EY's Global Delivery Services as a Senior AI/ML Platform Operations Engineer, playing a pivotal role in shaping the future of AI and ML. This position focuses on operating, supporting, and enhancing enterprise machine learning and generative AI platforms.
Leverage your expertise in MLOps and LLMOps to manage model deployment, monitoring, API operations, and incident resolution. You will be the technical escalation point for production AI services, collaborating closely with diverse teams to ensure reliable, secure, and scalable AI capabilities.
This role offers the opportunity to contribute to a globally connected network, build exceptional career experiences, and be part of a team that’s building a better working world.
Provide essential day-to-day production and operational support for machine learning, generative AI, and large language model platforms across all environments.
Deploy, configure, and support machine learning models and associated inference services using robust MLOps and LLMOps practices. Monitor real-time workloads and restore degraded services within stringent SLAs.
Troubleshoot a wide range of issues including endpoint errors, latency, scaling problems, and dependency conflicts. Operate comprehensive model pipelines from training to retirement.
Support various aspects of AI platforms such as prompt templates, configuration management, and guardrails. Implement and maintain observability for model quality, performance, cost, and safety events.
Investigate production incidents using detailed logs and perform root cause analysis for recurring issues. Develop Python utilities, automation scripts, and dashboards to enhance operational efficiency.
Support enterprise integrations with leading AI services like OpenAI, Azure OpenAI, and AWS Bedrock. Ensure secure handling of sensitive data, API keys, and model artifacts.
Manage capacity planning, autoscaling, and cost optimization for AI workloads. Coordinate controlled releases using Git and CI/CD pipelines, including thorough testing and validation.
Handle complex incidents, service requests, and changes, while mentoring junior engineers. Create and maintain comprehensive operational documentation, including runbooks and knowledge bases.
We are seeking a seasoned Senior AI/ML Platform Operations Engineer with strong hands-on knowledge of MLOps and LLMOps practices. You should possess a deep understanding of operating model APIs and endpoints, with robust Python skills for automation and troubleshooting.
Experience with OpenAI APIs and AWS Bedrock services is crucial, alongside a solid grasp of machine learning and generative AI evaluation methods. The ability to interpret distributed system telemetry and strong incident management skills are essential.
To qualify, you should hold a Bachelor’s degree in a relevant field or possess equivalent professional experience. You need 5–8 years of experience in platform engineering, DevOps, or a related domain, with at least 2 years specifically supporting ML or generative AI workloads.
Practical experience with MLOps pipelines, production model deployments, and LLMOps is required. Familiarity with CI/CD, containerization, cloud monitoring, and secrets management is also necessary.
We value professionals who can manage complex production incidents, perform thorough root cause analysis, and handle production changes effectively. Experience working with distributed teams and supporting business-critical services under strict SLAs is expected.
A willingness to participate in 24/7 support rotations is also a requirement for this role.
EY Global Delivery Services ( EY GDS)
Technology