Machine Learning Engineer II - Inference Platform

Beatdapp is building advanced streaming integrity technology, focusing on ML inference systems for audio at scale. This role blends ML engineering, platform/infrastructure work, and inference systems to bridge audio processing and production deployment. You'll optimize GPU-bound inference containers, manage multi-cloud infrastructure, and ensure low-latency, high-throughput services.

• Build and tune inference containers (Dockerfile, GPU access, multi-cloud orchestration with ECS, Cloud Run, GKE, EKS).
• Optimize GPU instance performance: concurrency tuning, VRAM accounting, rate limiting, multi-GPU distribution.
• Conduct scale/stress testing and translate results into autoscaling and instance-sizing decisions.
• Operate Terraform stack across GCP and AWS (networking, identity, GPU nodes, autoscaling).
• Build and maintain customer-facing API layer (authentication, rate limiting, data isolation, metering).
• Maintain data orchestration pipelines for model evaluation, reporting, and dashboards.
• Set up observability metrics, dashboards, logging, and alarms for inference service, instances, and models.

• Related STEM degree (BSc, MSc or higher) with 3+ years experience in platform/infra/backend/ML/applied-ML/data engineering.
• Strong engineering skills: write clean, scalable, production-grade code in Python, Go, Rust, or C++.