Senior LLM Runtime Performance Engineer

Bitdeer Technologies Group in Singapore is seeking a Senior Inference Runtime Engineer to own the performance-critical serving layer of our MaaS platform. You will optimize the runtime stack behind OpenAI- and Anthropic-compatible APIs to make self-hosted LLMs faster, cheaper, and more reliable.

Joining our team means working across GPU memory, batching, and deployment, mentoring, and turning benchmark results into production improvements while maintaining strict latency and cost targets.