Senior Lead AI Infra Engineer for LLM Ops

Hackajob Ltd; Glasgow; On-site; GBP 90,000 - 110,000; Full time

Job summary

hackajob Ltd. in the United Kingdom seeks a Senior Lead Software Engineer for the AI and ML Platform team to design and scale production AI infrastructure. You will lead reliability for LLM endpoints and build backend services for dependable AI operations.

Responsibilities include deploying LLMs on cloud and on-prem GPUs, managing containers via Kubernetes, and implementing observability, CD pipelines, and cost-efficient scaling.

Qualifications

• Advanced Python for production-grade services
• Strong SRE practices incl. incident management and runbooks
• Experience with cloud infra and IaC tooling for lifecycle management
• Kubernetes and container orchestration in cloud and on-prem
• Hosting and serving large language models on cloud and local GPUs
• Observability across metrics, logs, and traces

Responsibilities

• Design, develop, troubleshoot, and deliver production software for AI infra
• Build backend services and APIs for reliable AI infrastructure
• Operate and scale LLM serving infra across cloud and on-prem clusters
• Lifecycle-manage open-source and proprietary LLMs using IaC and CD pipelines
• Implement observability dashboards and alerting for GPUs/workloads
• Lead reliability engineering for LLM endpoints, capacity planning, and incident response
• Automate remediation to improve platform stability and developer experience
• Drive enterprise AI practices to improve code quality and delivery speed

Skills

Python

Kubernetes

Cloud

Machine Learning

Reliability Engineering

Observability

AI/ML Platform

Tools

Infrastructure as Code

CI/CD

Monitoring

Job description

hackajob Ltd. in the United Kingdom seeks a Senior Lead Software Engineer for the AI and ML Platform team to design and scale production AI infrastructure. You will lead reliability for LLM endpoints and build backend services for dependable AI operations.

Responsibilities include deploying LLMs on cloud and on-prem GPUs, managing containers via Kubernetes, and implementing observability, CD pipelines, and cost-efficient scaling.