Staff ML Platform Engineer (MLOps)

What you'll do

• Assess existing data and ML workflows, then prioritize and build platform improvements.
• Develop infrastructure for reproducible training and serving, LLM routing and evaluation, safe model experiments, and ML observability.
• Operate production models, troubleshoot incidents, and establish shared deployment and monitoring standards.

What they ask for

• Hands-on staff-level experience in MLOps, ML platform, or ML infrastructure; equivalent backgrounds with strong platform ownership are also considered.
• Experience establishing MLOps practices end to end, including model CI/CD, experiment tracking, registries, deployment, and monitoring.
• Production experience operating LLM-based systems, or traditional ML systems with ability to learn LLM tooling quickly; experience with batch and real-time serving.
• Hands-on experience with compute and environments, production experiments, ML observability and traceability, incident response, data pipelines and features, and systems design.

Nice to have

• Feature store experience; interest in moving into model development.
• Experience assessing AI/ML observability or LLM evaluation vendors, mission-driven or workforce data environments, or mentoring a small team.

Pay

USD $172,000-$215,000 (United States), pay range; CAD $172,000-$220,000 (Canada), pay range.

Tools

SQL, Python, Airflow, dbt, PostgreSQL, Redshift, MongoDB, AWS SageMaker

AI focus

Build infrastructure for LLM-powered product features, including cost-aware model routing and prompt and response evaluation; also support production ML models and recommendations.