Senior ML Platform Engineer: Real-Time Inference

Coinbase, Inc.; Concord (NH); Hybrid; USD 191,000 - 225,000; Full time

Job summary

Coinbase, Inc. is seeking a Senior Machine Learning Platform Engineer to build and operate the foundational infrastructure powering feature engineering, model training, and model serving across the company.

You will own ML inference infrastructure, streaming pipelines for fresh feature data, and distributed training systems, shaping how ML scales with the business. Expect to mentor engineers and contribute to high-quality production software.

Qualifications

• 5+ years of industry experience as a software engineer with ownership of distributed systems in production.
• Built and operated low-latency data or ML infrastructure (streaming pipelines, online serving systems, or distributed training) at scale.
• Track record of mentoring engineers and raising engineering quality through code reviews and design reviews.
• Familiarity with ML platform components (feature stores, model serving frameworks, training orchestration) to partner with ML engineers.
• Uses generative AI responsibly, with human oversight to deliver business-ready outputs and improve workflow efficiency, cost, and quality.

Responsibilities

• Own the design and reliability of ML inference infrastructure serving predictive models and LLMs, with high availability and low latency.
• Build and optimize low-latency streaming pipelines delivering fresh feature data to production ML models.
• Drive improvements to distributed training infrastructure to process large data volumes efficiently.
• Develop observability tooling to monitor data quality entering models and detect degradations affecting performance.
• Mentor junior engineers to raise the team's production-grade software standards.

Skills

Distributed systems

Low-latency infrastructure

Mentoring

ML platform components

Responsible AI

Job description

Coinbase, Inc. is seeking a Senior Machine Learning Platform Engineer to build and operate the foundational infrastructure powering feature engineering, model training, and model serving across the company.

You will own ML inference infrastructure, streaming pipelines for fresh feature data, and distributed training systems, shaping how ML scales with the business. Expect to mentor engineers and contribute to high-quality production software.