Description
We are seeking an experienced professional to join our team in the role of Senior Consultant Specialist (Model Hosting/Inference Optimization). As a key member of our AI platform team, you will collaborate closely with AI researchers, data scientists, software engineers, and product teams to deliver production-grade solutions that combine optimized inference, reliable hosting, and flexible fine-tuning capabilities for a wide range of AI models.
Principal responsibilities:
- Design, build, and operate scalable, reliable model hosting platforms for LLMs, embeddings, and STT/TTS across heterogeneous hardware.
- Drive inference optimisation for latency, throughput, and cost (quantisation, KV-cache optimisation, dynamic/continuous batching).
- Evaluate, integrate, and tailor inference frameworks (e.g., vLLM, TensorRT-LLM, SGLang) to maximise performance on target hardware.
- Own inference health and performance monitoring: latency, throughput, TTFT, memory, availability; troubleshoot bottlenecks and deployment issues.
- Partner with hardware teams to apply hardware-specific optimisations and improve resource utilisation.
- Ensure hosting systems meet production standards for reliability, scalability, security, and high availability.
- Build end-to-end, scalable fine-tuning pipelines to adapt foundation models using domain datasets.
- Work with data scientists/domain experts to define objectives and metrics, validate results, and integrate fine-tuned models into the hosting/inference stack.
Requirements:
- Bachelor’s/Master’s/PhD in ML/NLP/CS/Data Science/Statistics (or related).
- 3 years on AI platforms, covering both model hosting/inference optimisation and fine-tuning pipelines; LLM experience strongly preferred.
- Strong engineering skills in Python and CUDA, with solid understanding of GPU/CPU architecture and HPC fundamentals.
- Deep inference expertise: KV-cache, batching, quantisation (INT4/FP8/GPTQ/AWQ), operator optimisation, and framework integration (vLLM, TensorRT-LLM, SGLang); hands-on hosting on Docker/Kubernetes and AWS/GCP/Azure.
- End-to-end fine-tuning expertise: data prep, distributed training, hyperparameter tuning, HF/Accelerate/LoRA/QLoRA; plus benchmarking/monitoring/troubleshooting, AI-native mindset, and effective use of coding assistants.
You’ll achieve more when you join HSBC. HSBC is an equal opportunity employer committed to building a culture where all employees are valued, respected and opinions count. We take pride in providing a workplace that fosters continuous professional development, flexible working and, opportunities to grow within an inclusive and diverse environment.