MLOps Engineer (LLM/GenAI)

Job summary

HSBC is seeking an MLOps Engineer (LLM/GenAI) to engineer production-grade infrastructure for modern AI, focusing on hosting LLMs and optimizing inference performance.

Qualifications

• Extensive experience in building AI platforms and fine-tuning pipelines
• Strong Python and CUDA engineering skills
• Deep inference optimisation expertise
• Production hosting experience with Docker/Kubernetes and cloud platforms
• End-to-end fine-tuning expertise

Responsibilities

• Design, build, and operate scalable model hosting platforms for LLMs, embeddings, and STT/TTS
• Optimise inference for latency, throughput, and cost
• Evaluate and integrate inference frameworks to maximise performance
• Monitor inference health and troubleshoot issues
• Build end-to-end fine-tuning pipelines and integrate models

Skills

Relocation