AI Platform Test Engineer

China Mobile International Limited; Kuala Lumpur; On-site; MYR 120,000 - 180,000; Full time

Benefits offered by this job

Competitive remuneration

Medical and insurance benefits

Professional development and certifi c

Exposure to enterprise AI platforms

Opportunity to shape quality standards

Job summary

China Mobile Malaysia is seeking an AI Platform Test Engineer to ensure the quality, reliability and performance of our enterprise large language model (LLM) training and inference platform. You will test the workflows that matter in production - from model deployment and compute scheduling to APIs, access control, billing and rate limiting.

This role is ideal for a hands‑on quality engineer who enjoys combining software testing, automation, performance engineering and model evaluation.

Qualifications

• A bachelor's degree in computer science, software engineering, AI or related field, or equivalent practical experience.

Responsibilities

• Design and execute functional, API, integration and end-to-end test plans for LLM workflows.
• Build and maintain automated test frameworks and integrate regression testing into CI/CD pipelines.
• Run performance and load tests for inference services, analysing QPS/TPS, TTFT, TPOT, latency and concurrency.
• Compare performance across GPU/accelerator hardware, inference frameworks and deployment configurations.
• Evaluate model quality using benchmarks and business datasets.
• Own defect tracking, root‑cause collaboration, quality reports and release recommendations across R&D, Product and Operations teams.

Skills

Software testing

API testing

Test automation

Python

CI/CD

Load testing

Education

Bachelor's degree in computer science or related field

Tools

pytest

requests

Postman

Locust

JMeter

wrk

Docker

Kubernetes

Job description

China Mobile Malaysia is looking for an AI Platform Test Engineer to help ensure the quality, reliability and performance of our enterprise large language model (LLM) training and inference platform. You will test the workflows that matter in production - from model deployment and compute scheduling to APIs, access control, billing and rate limiting.

This role is ideal for a hands‑on quality engineer who enjoys combining software testing, automation, performance engineering and model evaluation. Your work will directly influence release quality, platform stability and the experience of enterprise customers using generative AI services.

What You'll Own

• Design and execute functional, API, integration and end-to-end test plans for LLM training and inference workflows.


• Build and maintain automated test frameworks using Python and integrate regression testing into CI/CD pipelines.


• Run performance and load tests for inference services, analysing QPS/TPS, time to first token (TTFT), time per output token (TPOT), latency and concurrency.


• Compare performance across GPU or accelerator hardware, inference frameworks such as vLLM and SGLang, batching strategies and deployment configurations.


• Evaluate model quality using benchmarks such as MMLU, C-Eval, CMMLU, GSM8K and HumanEval, together with business‑specific datasets.


• Own defect tracking, root‑cause collaboration, quality reports and release recommendations across R&D, Product and Operations teams.

What Success Looks Like

• Automated regression coverage expands and critical platform workflows are validated consistently before release.


• Clear performance baselines and model‑quality gates help teams make faster, evidence‑based release decisions.


• Reliability risks and infrastructure bottlenecks are identified early, communicated clearly and driven to resolution with the relevant engineering teams.

What You'll Bring

• A bachelor's degree in computer science, software engineering, artificial intelligence or a related field, or equivalent practical experience.


• Three or more years of software testing experience, including platform, API or back‑end service testing.


• Strong knowledge of test design, automation, defect management and quality assurance practices.


• Proficiency in Python and experience with tools such as pytest, requests, Postman, Locust, JMeter or wrk.


• Working knowledge of Docker, Kubernetes and testing in cloud‑native or containerised environments.


• Ability to interpret monitoring and load‑test data and communicate clear, evidence‑based recommendations.

What We Offer

• A competitive remuneration package and performance‑based incentives.


• Medical and insurance benefits in line with company policy.


• Professional development, technical learning and certification support.


• Exposure to enterprise AI platforms, LLM infrastructure and regional technology collaboration.


• The opportunity to shape quality standards for a growing enterprise AI business.