ML/AI Engineer: Scalable ML Ops & GPU Inference

Lloyds Bank plc; Manchester; Hybrid; GBP 73,000 - 81,000; Full time

Benefits offered by this job

Hybrid Working

Job Share

Pension contribution up to 15%

Annual bonus

Share schemes

30 days holiday

Wellbeing initiatives

Parental leave

Job summary

Lloyds Bank plc in Manchester is hiring an ML/AI Engineer to build and operate scalable ML systems and production‑grade Kubernetes clusters. You will lead GPU‑backed inference, model deployment, and end‑to‑end automation across dev, pre‑prod, and prod environments.

You will implement GitOps, CI/CD pipelines with Harness, and monitoring, ensuring reliable, auditable AI systems with a focus on fairness and safety. Hybrid working with strong growth potential.

Qualifications

• Strong Python for automation and service development.
• Deep expertise in Kubernetes, Docker, Helm, and GitOps.
• CI/CD with Harness; multi‑stage pipelines and environment promotion.
• CUDA, TensorRT, Triton, TorchServe; GPU scheduling experience.

Responsibilities

• Compose, build, and operate production‑grade Kubernetes clusters for model inference and training jobs.
• Configure autoscaling, resource quotas, GPU/CPU node pools, service mesh, Helm charts and operators.
• Implement GitOps workflows for environment configuration and releases.
• Build CI/CD pipelines in Harness to automate build, test, packaging and deployment across environments.
• Enable progressive delivery, blue/green/canary, with quality gates and model evaluation checks.
• Standardise pipelines for continuous training and monitoring to keep models fresh.

Skills

Python

Kubernetes

GitOps

Docker

CI/CD

CUDA

Tools

Harness

TensorRT

Triton

TorchServe

MLflow

Prometheus

Grafana

Job description

Lloyds Bank plc in Manchester is hiring an ML/AI Engineer to build and operate scalable ML systems and production‑grade Kubernetes clusters. You will lead GPU‑backed inference, model deployment, and end‑to‑end automation across dev, pre‑prod, and prod environments.

You will implement GitOps, CI/CD pipelines with Harness, and monitoring, ensuring reliable, auditable AI systems with a focus on fairness and safety. Hybrid working with strong growth potential.