Staff ML Inference Engineer - Production Serving WFH

Cloudera; Singapore; Hybrid; SGD 180,000 - 240,000; Full time

Benefits offered by this job

Generous PTO Policy

Flexible WFH Policy

Phone and Internet Reimbursement

Continued Career Development

Paid Volunteer Time

Employee Resource Groups

EEO/VEVRAA

Job summary

Cloudera is seeking a Staff ML Inference Engineer to design and optimize production model-serving pipelines using Cloudera AI Inference across hybrid environments. You will translate customer requirements into reliable endpoints, benchmark workloads, and drive practical performance improvements.

The role focuses on inference engineering, GPU optimization, and scalable tooling, with collaboration across platform and applied AI teams to deliver reusable deployment guidance.

Qualifications

• 8+ years in ML systems, software, distributed systems, or performance engineering with leadership.
• Production GPU-based model-serving experience with at least one inference stack (NVIDIA NIM, vLLM, SGLang, TensorRT-LLM, Triton).
• Strong Python, Linux, containers, and Kubernetes foundations for serving stack diagnostics.
• Experience benchmarking and improving inference performance and understanding latency/throughput trade-offs.

Responsibilities

• Deploy and optimize production model-serving solutions across on-premises, private-cloud, and public-cloud environments.
• Develop repeatable benchmarks for input/output lengths, request rates, and concurrency to guide GPU/config choices.
• Diagnose bottlenecks across runtimes, GPU compute/memory, CPU, networking, and I/O; evaluate optimization techniques.
• Build benchmarking, profiling, diagnostic, and validation tooling to reproduce customer scenarios and measure latency and GPU memory use.
• Collaborate with customers and platform/engineering teams to translate findings into deployments and product improvements.

Skills

Python

Linux

Containers

Kubernetes

ML Systems

Performance Engineering

Profiling

Tools

NVIDIA NIM

vLLM

SGLang

TensorRT-LLM

Triton

NVIDIA Nsight

Job description

Cloudera is seeking a Staff ML Inference Engineer to design and optimize production model-serving pipelines using Cloudera AI Inference across hybrid environments. You will translate customer requirements into reliable endpoints, benchmark workloads, and drive practical performance improvements.

The role focuses on inference engineering, GPU optimization, and scalable tooling, with collaboration across platform and applied AI teams to deliver reusable deployment guidance.