HSBC

4 hours ago

Sr. Associate Director, Software Engineering (Model Hosting Pod Tech Lead)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 4 hours agoStatus: Live

Job Summary

Lead the engineering of HSBC’s AI model hosting and inference optimization platform under the CTO Platforms (AI Platform). Own scalable model hosting systems, inference optimization (latency/throughput/cost), and integration of inference frameworks, while also building end-to-end fine-tuning pipelines. Manage a high-performing engineering team, deliver roadmap outcomes, and partner with hardware teams to ensure reliable, secure, high-availability production workloads.

Location: Shenzhen, Guangzhou, Xi'an

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Seniority: Sr. Director level

Key Responsibilities

•Design, build, and maintain scalable, reliable AI model hosting systems for large-scale deployment across diverse hardware platforms.
•Develop inference optimization strategies to improve low latency, high throughput, and cost efficiency (including quantization, KV cache optimization, and continuous batching).
•Evaluate, integrate, and customize inference frameworks (vLLM, TensorRT-LLM, SGLang) to optimize performance on target hardware.
•Build end-to-end model fine-tuning pipelines and integrate fine-tuned models into hosting/inference infrastructure for deployment.
•Lead and develop an engineering team and own delivery outcomes end-to-end (roadmap planning, prioritization, stakeholder management, execution).

Key Requirements

•Bachelor’s/Master’s/PhD in Machine Learning, NLP, Computer Science, Data Science, Statistics, or a related field.
•5+ years of AI experience with proven expertise in model inference optimization/hosting and model fine-tuning pipeline development (LLM experience a plus).
•3+ years leading teams, including people management and delivery ownership.
•Proficiency in Python and CUDA; familiarity with GPU/CPU architecture and HPC principles.
•Hands-on expertise with inference and fine-tuning technologies such as KV cache management, quantization (INT4/FP8/GPTQ/AWQ), vLLM/TensorRT-LLM/SGLang, and Docker/Kubernetes with cloud platforms (AWS/GCP/Azure).

Experience:3+ yearsAILLMsMachine learningHPCCloudInference optimization

Education:

Skills:LeadershipCoachingPerformance managementStakeholder managementTroubleshooting

Tech Stack:PythonCUDADockerKubernetesAWSGCPAzureVLLMTensorRT-LLMSGLangHugging Face TransformersAccelerateLoRAQLoRAINT4FP8GPTQAWQKV cacheBatch processing

Company Brief

HSBC

Global banking and financial services organisation offering retail, commercial, corporate and investment banking, wealth management, and global markets services across Europe, Asia, the Americas and the Middle East.

Industry: Banking

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: London, United Kingdom

Founded: 1865

Glassdoor: 3.6

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

HSBC

4 hours ago

Sr. Associate Director, Software Engineering (Model Hosting Pod Tech Lead)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 4 hours agoStatus: Live

Job Summary

Location: Shenzhen, Guangzhou, Xi'an

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Seniority: Sr. Director level

Key Responsibilities

•Design, build, and maintain scalable, reliable AI model hosting systems for large-scale deployment across diverse hardware platforms.
•Develop inference optimization strategies to improve low latency, high throughput, and cost efficiency (including quantization, KV cache optimization, and continuous batching).
•Evaluate, integrate, and customize inference frameworks (vLLM, TensorRT-LLM, SGLang) to optimize performance on target hardware.
•Build end-to-end model fine-tuning pipelines and integrate fine-tuned models into hosting/inference infrastructure for deployment.
•Lead and develop an engineering team and own delivery outcomes end-to-end (roadmap planning, prioritization, stakeholder management, execution).

Key Requirements

•Bachelor’s/Master’s/PhD in Machine Learning, NLP, Computer Science, Data Science, Statistics, or a related field.
•5+ years of AI experience with proven expertise in model inference optimization/hosting and model fine-tuning pipeline development (LLM experience a plus).
•3+ years leading teams, including people management and delivery ownership.
•Proficiency in Python and CUDA; familiarity with GPU/CPU architecture and HPC principles.
•Hands-on expertise with inference and fine-tuning technologies such as KV cache management, quantization (INT4/FP8/GPTQ/AWQ), vLLM/TensorRT-LLM/SGLang, and Docker/Kubernetes with cloud platforms (AWS/GCP/Azure).

Experience:3+ yearsAILLMsMachine learningHPCCloudInference optimization

Education:

Skills:LeadershipCoachingPerformance managementStakeholder managementTroubleshooting

Tech Stack:PythonCUDADockerKubernetesAWSGCPAzureVLLMTensorRT-LLMSGLangHugging Face TransformersAccelerateLoRAQLoRAINT4FP8GPTQAWQKV cacheBatch processing

Company Brief

HSBC

Industry: Banking

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: London, United Kingdom

Founded: 1865

Glassdoor: 3.6

Website LinkedIn