MLOps Engineer (LLM/GenAI) (Sheffield)

Job Description

hackajob is collaborating with HSBC to connect them with exceptional professionals for this role.

\n

This is a hybrid role, based in Sheffield, UK 

\n

In this role, you will:

\n

\n
• Design, build, and operate scalable model hosting platforms for LLMs, embeddings, and STT/TTS across heterogeneous hardware

\n

• Optimise inference for latency, throughput, and cost (e.g., quantisation, KV-cache optimisation, dynamic/continuous batching)

\n

• Evaluate and integrate inference frameworks (e.g., vLLM, TensorRT-LLM, SGLang) to maximise performance on target hardware

\n

• Own inference health/performance monitoring (latency, throughput, TTFT, memory, availability) and troubleshoot bottlenecks/deployment issues

\n

• Build end-to-end fine-tuning pipelines (data prep → distributed training → validation) and integrate fine-tuned models into the hosting/inference stack

\n\n

To be successful in this role you should have the following skills:

\n

\n
• Extensive experience in building AI platforms covering model hosting/inference optimisation and fine-tuning pipelines (LLM experience strongly preferred)

\n

• Strong Python and CUDA engineering; solid understanding of GPU/CPU architecture and HPC fundamentals

\n

• Deep inference optimisation expertise: KV-cache, batching, quantisation (INT4/FP8/GPTQ/AWQ), operator optimisation, framework integration (vLLM/TensorRT-LLM/SGLang)

\n

• Production hosting experience with Docker/Kubernetes and cloud platforms (AWS/GCP/Azure)

\n

• End-to-end fine-tuning expertise: data preparation, distributed training, hyperparameter tuning, HF/Accelerate/LoRA/QLoRA, plus benchmarking/monitoring/troubleshooting

\n