Senior AI Platform Engineer — End-to-End Deployment

A*STAR - Agency for Science, Technology and Research

Singapore

On-site

SGD 120,000 - 180,000

Full time

4 days ago

Be an early applicant

Application generator

Don’t send a generic resume — generate a resume and cover letter tailored to this exact role.

Get past ATS filters

Job summary

A*STAR - Agency for Science, Technology and Research is seeking an experienced software engineer to translate AI research prototypes into a robust, deployed system for evaluation. You will work with researchers, solution architects and engineers to integrate ASR, NLU, LLM and multi-agent components into an end-to-end platform.

The role emphasizes strong software engineering, full-stack development and dependable delivery rather than model research alone.

Qualifications

Bachelor's or Master's degree in Computer Science, Software Engineering, Computer Engineering, Information Systems or a related technical discipline.
Strong programming skills and demonstrated ability to build reliable software systems.
Strong full-stack development experience covering backend services/APIs and modern web application development.
Solid understanding of software architecture, data structures, concurrency, networking fundamentals and distributed/service-oriented systems.
Hands-on experience with Linux-based development and deployment environments.
Experience with Git, automated testing and disciplined software development practices.
Demonstrated ability to debug complex end-to-end systems and resolve issues across multiple software layers.
Strong delivery mindset: able to take technical work from requirements and prototype through integration, testing and demonstrable working software.
Good written and verbal communication skills and ability to work effectively with research, engineering and domain-expert teams.

Responsibilities

End-to-End System Integration and Deployment.
Package and deploy AI inference services and supporting application components.
Implement and maintain interfaces between the Audio Extraction Gateway, AI inference platform and user-facing applications.
Support integration with web endpoints, audio codecs, metadata flows and industry-grade interfaces.
Build deployment configurations reproducible across dev, test, simulated and operational environments.
Full-Stack Application Development for backend services, APIs and real-time processing.
Develop or support operator-facing web interfaces and dashboards.
Implement service-to-service communication, asynchronous processing and state management.
Build admin, configuration and diagnostic functions for testing and deployment support.
Collaborate with UI/UX and end-user stakeholders to translate requirements into software features.
Write clean, modular and testable code with documentation and config management.
Profile and optimize latency, throughput, memory usage and GPU utilization.
Implement timeout, retry, health-check and degraded-mode behaviours.
Conduct load and stress testing on target hardware and identify bottlenecks.
Develop containerized deployment workflows and automated build, test and release processes.
Maintain environment configuration, dependency management and reproducible artefacts.
Implement logging, metrics, tracing and diagnostic tooling.
Support secure deployment within restricted environments with access control and data handling policies.
Support infrastructure setup for inference servers and demo environments.
Contribute to deployment and troubleshooting documentation.