Support application integrations through APIs, secure file transfer, and messaging technologies to enable reliable data exchange across systems and organizations.
Working RequirementsFully onsite at Menara Sentral RAC, Kuala Lumpur.Independent contractor arrangement; EPF and SOCSO contributions are self-managed.Able to work with cross-functional teams on AI development, integration, testing, and deployment.
Follow up on cutting-edge technologies such as global large model inference, GPU high-performance computing, distributed parallelism, and cache optimization, benchmark against mainstream inference frameworks such as vLLM and TensorRT-LLM, complete the implementation of solutions and technological innovation, continuously iterate and optimize the performance and cost advantages of the inference system, and build the core technological barriers of the team.
Work with partners to define processes and develop internal and external tools for core operations (user ops, safety ops, developer ops, and service reliability)
Make integration effortless: Create reusable frameworks, SDKs, and configuration patterns so new connectors and integrations can be built quickly and maintained reliably.