Senior Machine Learning Engineer

Recruiting From Scratch•San Francisco, CA

1d•Onsite

About The Position

The Senior Machine Learning Engineer will build and evolve the machine learning detection platform of an early-stage cybersecurity company. The platform uses machine learning and behavioral analysis to detect and prevent account compromise and sophisticated email-based attacks, identifying suspicious activity in real time while minimizing false positives. The role has significant ownership over core systems and involves close collaboration with technical leadership and customers. The engineer will research, select, train, and deploy models suited to the detection problems and available data; explore new signals and modeling approaches; and apply techniques such as behavioral modeling, anomaly detection, statistical methods, and NLP. They will take models from experimentation through production, monitor live performance, and improve accuracy, scalability, and reliability. The position also involves building real-time data pipelines, feature infrastructure, and inference systems; designing for increasing data volumes and customer usage; and making architectural decisions related to performance and high-throughput processing. The engineer will own meaningful platform components end to end, contribute to engineering standards and technical direction, and work with customers to translate security needs and emerging attacks into improved detection capabilities. This is an on-site role in San Francisco, five days per week. The company does not offer visa sponsorship; applicants must be authorized to work in the United States without current or future sponsorship.

Requirements

3–8 years of experience in machine learning engineering; the posting notes that at least 4 years is preferred based on the role requirements.
Strong experience building, training, and deploying machine learning models in production using Python.
Experience with real-time or streaming data pipelines and large-scale production systems.
Strong quantitative fundamentals, including probability, statistics, and linear algebra.
Experience with anomaly detection, behavioral modeling, NLP, or other relevant machine learning techniques.
Strong software engineering fundamentals and ability to build clean, maintainable production code.
Experience owning machine learning systems end to end, beyond experimentation or notebook-based modeling.
Understanding of feature stores, high-performance databases, and distributed systems.
Ability to evaluate modeling approaches and understand their strengths, limitations, and trade-offs.
Comfort working with significant autonomy in a small, fast-moving engineering team.
Strong ownership and ability to take a problem from identification through implementation and production rollout.
Must be authorized to work in the United States without current or future visa sponsorship.

Nice To Haves

Experience in cybersecurity, fraud detection, account takeover prevention, or threat detection.
Experience working with high-volume behavioral or event data.
Background in quantitative finance, trading systems, or other high-stakes data environments.
Experience building real-time anomaly detection or risk-scoring systems.
Experience designing feature pipelines and high-performance machine learning infrastructure.
Experience working in an early-stage startup or lean engineering team.
Familiarity with Node.js, TypeScript, or React; described as helpful but not a core requirement.

Responsibilities

Design, build, and evolve machine learning models to identify account compromise and suspicious behavior in real time.
Work with technical leadership to develop the core detection platform and improve identification of emerging attack patterns.
Research, select, train, and deploy models based on detection problems and available data.
Explore new signals and modeling approaches to improve detection coverage while minimizing false positives.
Apply behavioral modeling, anomaly detection, statistical methods, and NLP to identify security threats.
Take machine learning models from experimentation and research through production deployment.
Monitor model performance in live environments and continuously improve accuracy, scalability, and reliability.
Build and optimize real-time data pipelines, feature infrastructure, and production inference systems.
Design systems to support significant increases in data volume and customer usage.
Make architectural decisions concerning performance, scalability, and high-throughput data processing.
Own meaningful parts of the machine learning detection platform end to end.
Work directly with customers to understand attacks and identify opportunities for better detection.
Collaborate with the CTO and machine learning leadership on technical direction and modeling decisions.
Establish engineering standards, contribute to architectural decisions, and improve platform quality.
Identify problems, propose solutions, and execute improvements across the system.