Lead ML Inference & Optimization Engineer

ThoughtWorks; Singapore; On-site; SGD 100,000 - 125,000; Full time

Job summary

A global technology consultancy in Singapore is looking for a Technical Lead in model optimization. In this role, you will lead the design and implementation of advanced optimization pipelines while mentoring engineering teams. Candidates should have deep expertise in model and runtime optimization techniques, as well as strong proficiency in deep learning frameworks. This position offers meaningful growth and career development opportunities.

Benefits

Interactive career development tools

Numerous development programs

Supportive team culture

Qualifications

• Deep practical expertise in advanced model optimization techniques.
• Proven experience optimizing inference workloads in production.
• Ability to diagnose and optimize performance using various tools.

Responsibilities

• Lead design and implementation of model optimization pipelines.
• Guide teams in high-throughput serving strategies.
• Develop benchmarks and performance dashboards for system efficiency.

Skills

Model and runtime optimization techniques

Deep learning frameworks (PyTorch, TensorFlow)

Profiling tools (Nsight, PyTorch/TensorFlow profilers)

Communication and stakeholder engagement skills

Experience designing scalable inference systems

Tools

vLLM

NVIDIA Triton

Dynamo

Job description

A global technology consultancy in Singapore is looking for a Technical Lead in model optimization. In this role, you will lead the design and implementation of advanced optimization pipelines while mentoring engineering teams. Candidates should have deep expertise in model and runtime optimization techniques, as well as strong proficiency in deep learning frameworks. This position offers meaningful growth and career development opportunities.