Machine Learning Engineer II - Inference Platform

About the Company

Beatdapp is a company delivering the most advanced streaming integrity technology in the world. One of our ventures is building machine learning inference systems for audio at scale, focusing on music, podcasts, and speech, with a particular focus on AI-generated sound.

Responsibilities

• Build, tune, and ship inference containers using Docker and multi-cloud orchestration (ECS, Cloud Run, GKE, EKS)
• Optimize in-container performance including concurrency tuning, VRAM accounting, and multi-GPU distribution
• Build and run scale and stress testing scenarios to characterize latency-vs-throughput curves
• Operate Terraform stacks across GCP and AWS, managing networking, identity, and GPU nodes
• Build and extend the customer-facing API layer for authentication, rate limiting, and metering
• Maintain data orchestration pipelines for model evaluation and operational dashboards
• Build and tune observability metrics, dashboards, and logging across service, instance, and model layers

Requirements

• STEM degree (BSc, MSc, or higher)
• 3+ years of experience in platform, infrastructure, backend, ML, or data engineering
• Proficiency in Python or performance-oriented languages like Go, Rust, or C++
• Architectural fluency in distributed systems, data stores, and caching
• Experience with data engineering tools like Airflow, BigQuery, or Postgres
• Deep cloud infrastructure and networking experience (GCP or AWS)
• Experience with ML platform tooling such as MLflow
• Proficiency with Terraform and Infrastructure as Code
• Strong CI/CD discipline and observability instincts
• Experience with inference performance tuning (micro-batching, concurrency, request queueing)

Preferred Qualifications

• Experience with audio or media systems
• Signal processing or speech detection expertise
• Computer vision experience
• GPU work including CUDA, kernels, or drivers
• Experience with streaming systems like Kafka, Pub/Sub, or Kinesis