Senior LLM Inference Performance Engineer

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

Responsibilities

include tuning runtimes, profiling bottlenecks, onboarding models, and defining safe defaults for high-value inference workloads. Join a fast-growing team shaping AI-powered mining and cloud services. J-18808-…