LLM/GenAI MLOps Engineer - Platform Architect

HSBC; Sheffield; On-site; GBP 60,000 - 80,000; Full time

Benefits offered by this job

Private healthcare

Contributory pension scheme

Enhanced maternity and adoption pay

Job summary

慨正橡扯 is seeking an MLOps Engineer (LLM/GenAI) based in Sheffield, UK, to engineer production-grade infrastructure for modern AI. The ideal candidate will design scalable model hosting platforms, optimise inference performance, and build fine-tuning pipelines.

This role requires deep expertise in AI platforms, particularly in LLMs, and strong skills in Python and CUDA. The successful candidate will enjoy competitive pay and benefits, including private healthcare and a contributory pension scheme.

Qualifications

• Extensive experience in building AI platforms with LLM experience preferred.
• Strong Python and CUDA engineering skills required.
• Deep inference optimisation expertise needed.

Responsibilities

• Design and build scalable model hosting platforms for LLMs.
• Optimise inference for latency and throughput.
• Own inference health/performance monitoring.

Skills

AI platforms expertise

Python and CUDA engineering

Deep inference optimisation

Production hosting experience

End-to-end fine-tuning expertise

Tools

Docker

Kubernetes

AWS/GCP/Azure

Job description

慨正橡扯 is seeking an MLOps Engineer (LLM/GenAI) based in Sheffield, UK, to engineer production-grade infrastructure for modern AI. The ideal candidate will design scalable model hosting platforms, optimise inference performance, and build fine-tuning pipelines.

This role requires deep expertise in AI platforms, particularly in LLMs, and strong skills in Python and CUDA. The successful candidate will enjoy competitive pay and benefits, including private healthcare and a contributory pension scheme.