Senior ML Platform Engineer — Low-Latency Inference

Coinbase, Inc.; Atlanta (GA); Híbrido; USD 191 000 - 225 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Equity

401(k) plan

Medical/dental/vision insurance

Resumo da oferta

Coinbase, Inc. is seeking a Senior Machine Learning Platform Engineer to build and maintain the ML infrastructure powering feature engineering, model training, and model serving.

You will influence fraud detection, personalization, and blockchain analysis while supporting streaming, distributed training, and highly available inference services. You will own the systems behind low-latency inference, streaming pipelines, and scalable training, and you will mentor engineers to raise the team’s

Qualificações

• 5+ years as a software engineer with production distributed systems ownership.
• Built/operated low-latency data or ML infrastructure at scale.
• Mentored engineers and raised engineering quality through reviews.
• Familiarity with ML platform components (feature stores, model serving, orchestration).
• Uses generative AI responsibly with human oversight to improve workflow efficiency, cost, and quality.

Responsabilidades

• Own design and reliability of ML inference infrastructure with high availability and low latency at scale.
• Build and optimize low-latency streaming pipelines delivering fresh feature data to models.
• Improve distributed training infrastructure for efficient large-scale data processing.
• Develop observability tooling to monitor data quality and detect degradations affecting models.
• Mentor junior engineers to raise production-grade software standards.

Conhecimentos

Distributed systems

ML platform

Mentoring

Low-latency infra

Generative AI prudence

Descrição da oferta de emprego

Coinbase, Inc. is seeking a Senior Machine Learning Platform Engineer to build and maintain the ML infrastructure powering feature engineering, model training, and model serving.

You will influence fraud detection, personalization, and blockchain analysis while supporting streaming, distributed training, and highly available inference services. You will own the systems behind low-latency inference, streaming pipelines, and scalable training, and you will mentor engineers to raise the team’s