Detection Machine Learning Manager, Abnormal Security

• 2+ years experience of managing data driven (ML) product teams running at large scale data ( 100M+ ) and ability to guide a team technically in this respect
• 3+ years experience designing, building and deploying machine learning applications in one of the domains of text understanding, entity recognition, NLP experience, computer vision, recommendation systems, or search
• 4+ years of hands-on experience in building and safely shipping backend heavy product ML adjacent systems at high velocity
• Ability to understand business requirements thoroughly and bias toward guiding the team to build a simplest yet generalizable ML model / system that can accomplish the goal
• Metrics driven culture: Has led a team of engineers in building out systems and displayed the ability to define metrics of excellence and setup processes to continuously monitor and maintain high standards on metrics
• Be Customer obsessed: Worked with multiple stakeholders to gather requirements and then prioritize and balance against the team's roadmap
• Set High standards - sets high standards and expectations for project execution for themselves and the whole team
• This position involves access to technology that is subject to the U.S. Export Administration Regulations (EAR)
• As a result, candidates offered employment must be eligible to access controlled technology under U.S. export control laws. Employment in this position is conditioned on the availability of government authorization

Desirable

• Abnormal AI is looking for a Machine Learning Engineering Manager to lead the Attack Detection team
• At Abnormal, we protect our customers against nefarious adversaries who are constantly evolving their techniques and tactics to outwit and undermine the traditional approaches to Security
• The Attack Detection team’s mission statement is to provide world-class detector efficacy to tackle the ever changing adversarial attack landscape using a combination of generalizable and auto trained models as well as specific detectors for high value attack categories
• This team is solving a multi-layered detection problem, which involves modeling communication patterns to establish enterprise-wide baselines, incorporating these patterns as robust signals, and combining these signals with contextual information to create extremely precise systems
• The EM will report to the Senior EM of the Message Detection Team, and will lead a team that is primarily composed of machine learning engineers
• The EM will be responsible for managing the execution of the roadmap and deliverables while optimizing both human and system resource utilization
• The Engineering Manager’s success or failure impacts our ability to build and iterate on the detection decisioning system at an extremely high recall, enabling us to respond to current and future attacks
• Preventing such attacks which cause significant customer workflow disruption is the core of our business and that makes the success of this team, and its leader, so massively impactful
• Own the execution success of the quarterly roadmap for the Attack Detection team; engage continuously with the Tech Leads to help adjust and prioritize current roadmap items according to the team’s charter and company priorities
• Deliver on:
• Extremely high recall detector engine in an adversarial environment using model based as well as heuristic detectors
• Automated model retraining pipelines based continuous ML deployment system to automatically ‘learn’ from new patterns
• Text based signal models to capture and model suspiciousness of email content in multiple languages
• Own both directly customer impacting metrics and system metrics and able to work with the team to proactively identify new attacks and repair degradations:
• Recall ie False Negative metrics for our customer base across various attack types
• Overall attack and precision metrics for highly flagging generalized ML models
• Automation metrics for responses to customer specific requirements
• Own the machine learning feature consumption layer for both message metadata/content and current/historical user behavior type of signals and and systems and processes to continuously incorporate new features types into existing and new ML models
• Drive processes to enable the team to deliver on projects that are set by TLs as part of the technical roadmap
• Manage the quarterly roadmap updates, project time estimates, weekly sprint planning, day-to-day standups
• Identify risks on project delivery (technical, operational, dependency risks) and escalate to appropriate technical leads
• Able to assess progress in a metrics-oriented manner
• Provide continuous feedback
• Responsible for mentoring and growing the engineers on the team by providing constructive feedback at regular intervals to help them successfully execute high impact projects
• Drive Stakeholder alignment : Collaborate with the platform and infrastructure initiatives on company wide initiatives to help increase efficiency, customer adoption and engineer effectiveness goals
• Drive stakeholder alignment: Proactively identify and collaborate with platform and infrastructure teams on company-wide initiatives

• As part of Abnormal AI's secure hiring practices, we conduct video interviews and validate applicant identity at various stages through our recruitment process
• Further, if your application is successful and Abnormal AI makes a conditional offer of employment, we will carry out pre-employment checks which must be successfully completed to progress to a final offer
• All processes and pre-employment checks are in line with prevailing legislation and Abnormal AI's policies relevant to our security and privacy standards