Senior LLM Performance & Benchmark Engineer

Bitdeer (NASDAQ: BTDR); Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Bitdeer is seeking an experienced ML infrastructure engineer in Singapore to build benchmarks, manage model evaluation, and optimize performance for AI/cloud workloads. You will design gate criteria for model launches, maintain realistic workloads, and compare deployment options to optimize latency, cost, and reliability.

You will collaborate with runtime engineers and SRE to translate benchmark results into actionable SLOs and alerts, contributing to scalable and robust AI-enabled systems

Qualifications

• 5+ years in ML infrastructure, performance engineering, or backend testing.
• Experience with LLM serving metrics and model evaluation.
• Strong Python skills; Go is a plus.

Responsibilities

• Build benchmark pipelines for TTFT, inter-token latency, output throughput, request latency, concurrency curves, error rate, and GPU utilization.
• Create model launch gates covering OpenAI/Anthropic compatibility, streaming behavior, tool calling, reasoning output, multimodal behavior, and long-context cases.
• Maintain representative workloads using synthetic, replayed, and customer-like traffic patterns for both steady-state and burst scenarios.
• Compare model/runtime/provider options and publish clear recommendations for routing, fallback, pricing, and capacity decisions.
• Automate regression detection in CI/CD and staging so model, runtime, or configuration changes do not silently degrade quality, latency, or cost.
• Work with runtime engineers to identify bottlenecks and verify improvements; work with SRE to convert benchmark results into SLOs and alert thresholds.

Skills

ML infrastructure

Python

Go

Kubernetes

OpenAI/Anthropic APIs

Tools

CI/CD tooling

GPU benchmarking

Job description

Bitdeer is seeking an experienced ML infrastructure engineer in Singapore to build benchmarks, manage model evaluation, and optimize performance for AI/cloud workloads. You will design gate criteria for model launches, maintain realistic workloads, and compare deployment options to optimize latency, cost, and reliability.

You will collaborate with runtime engineers and SRE to translate benchmark results into actionable SLOs and alerts, contributing to scalable and robust AI-enabled systems