Leads the team this role joins
Runs the team day to day
Decides on early hires
From your own Gmail and LinkedIn.
About the role
This is a senior, on-site role in Hyderabad for an engineer who designs and runs machine learning and large language model inference platforms across AWS and Azure. The job centres on production inference pipelines, Kubernetes deployments, vLLM and REST services, event-driven design, CI/CD and GPU optimisation, and the engineer works with data science, cloud and platform teams. Optum is part of UnitedHealth Group, a health services organisation focused on helping people live healthier lives.
What you’ll do
- Build and maintain production machine learning and large language model inference pipelines.
- Deploy and manage machine learning workloads on Kubernetes, EKS and AKS.
- Build scalable inference services with vLLM and REST APIs.
- Design event-driven and asynchronous systems using queues and messaging services.
- Create CI/CD pipelines for models and inference services.
- Manage model versioning, promotion, rollback and release workflows.
- Tune inference for GPU use, latency, throughput, reliability and cost.
- Review peer code, architecture and technical designs, and drive engineering standards.
- Work with data scientists and platform teams on architecture and delivery decisions.
What they’re looking for
- Skills in Python, machine learning and large language model inference, AWS, Azure, Kubernetes, EKS or AKS, Docker, vLLM, REST APIs, CI/CD, event-driven architecture, GPU workloads and MLOps.
What’s on offer
- Benefits and compensation are not described in the posting.
Skills
Questions about this role
Is this role on site?
Yes. The listing is marked in office, based in Hyderabad.
What skills are required?
Python, machine learning and large language model inference, AWS, Azure, Kubernetes with EKS or AKS, Docker, vLLM, REST APIs, CI/CD, event-driven architecture, GPU workloads and MLOps.