Epicareer Might not Working Properly
Learn More

AI Engineer (Infra) for AI Singapore (Products)

Salary undisclosed

Checking job availability...

Original
Simplified
Job Description

Job Description

AI Singapore (AISG) is a national AI programme launched by the National Research Foundation (NRF) to anchor deep national capabilities in Artificial Intelligence (AI).

The programme office is hosted by the National University of Singapore (NUS) and brings together all Singapore-based research institutions and the vibrant ecosystem of AI start-ups and companies developing AI products to perform use-inspired research, grow the knowledge, create the tools, and develop the talent to power Singapore's AI efforts.

We are looking for an AI Engineer to join us in the AI Products Engineering Infra team. The selected candidate will jointly be responsible for the architecting, designing, building, testing and maintaining of AISG’s SEA-LION LLM API server farm.

Duties And Responsibilities

  • Manage high performance clusters (CPU/GPU/TPUs) and software configuration on different cloud provider
  • Develop new and re-iterate on existing software and system applications using software engineering best practices and AI technologies
  • Handle cloud resources on different cloud provider
  • Perform the necessary AI modelling, coding, testing, validation and deployment to ensure reliable and scalable AI solution
  • Maintain code repository and documentation standards
  • Collaborate with cross-functional teams within AI Products to design and resolve issues
  • Contribute to community engagement activities such as sharing via technical session meet-ups and article write-ups, and participating in discussion forums
  • Maintain LLM training codebase and implement new features

Qualifications

  • Degree in computer science, machine learning, AI, and other relevant equivalent quantitative fields
  • Experience in writing clean production level code in Python. Knowledge of other languages will be an advantage
  • Familiarity with Pytorch and Containerisation and/or orchestration technologies
  • Comfortable working in a UNIX environment and writing bash scripts
  • Certifications from any cloud provider, such as AWS, GCP, Azure etc will be an advantage but not mandatory

The Following Experiences Would Be Advantageous

  • Managing and optimising infrastructure and systems for AI workloads. Previous experience in deployment on cloud platforms (AWS/GCP/Azure) and/or edge devices
  • Large Language Model inference server deployment and optimisation for scalable AI applications eg. VLLM, TGI, Triton Inference Server
  • Maintaining Infrastructure as Code (IaC) for cloud resources provisioning eg. Terraform, CloudFormation
  • Using software configuration management such as Ansible
  • Familiar with job orchestrators, such as Slurm, Kubernetes or PBS

More Information

Location: Kent Ridge Campus

Organization: Office of the Deputy President(Res&Tech)

Department : AI Singapore

Employee Referral Eligible: No

Job requisition ID : 27709