Senior Machine Learning Engineer, Reliability

About the role

Roblox is seeking its first Senior Machine Learning Engineer to join the Reliability team. You will design and implement machine learning strategies to enhance platform stability by analyzing production data and automating incident response.

Key facts

What you'll do

• Create the strategic roadmap for applying machine learning to improve production system reliability.
• Build and refine real-time anomaly detection systems to decrease the time required to identify production issues.
• Engineer data pipelines that ingest logs, metrics, traces, and change management records.
• Construct a reasoning layer to analyze data streams and identify root causes for system failures.
• Design time-series models to forecast capacity needs and traffic surges to support automated scaling.

Requirements

• Expertise in advanced modeling techniques with the ability to tune models for specific production use cases.
• Experience architecting infrastructure that incorporates feedback loops from automated systems or users.
• Strong foundation in distributed systems and high-throughput, large-scale architectures.
• Ability to provide structure in ambiguous environments and communicate technical concepts to executive leadership.

Skills & tools

• Machine Learning modeling
• Distributed systems architecture
• Anomaly detection
• Time-series forecasting
• Data pipeline engineering

Practical notes

• Base salary range: $196,750 to $243,290 USD per year.
• Compensation includes equity and benefits.
• Onsite work is required Tuesday through Thursday, with optional office attendance on Monday and Friday.
• The company may be unable to support certain U.S. visa categories or provide H-1B sponsorship for this position.