• Track record of success in translating business requirements into scalable, maintainable systems with a bias toward simpler but iterative systems
• 4+ Experience with production ML systems - understands the pillars of a modern ML stack and the development, maintenance and tuning processes of ML models
• Uses a systematic approach to debug both data and system issues within ML / heuristics models
• Fluent with Python and machine learning libraries like numpy and scikit-learn
• Experience with data analytics and wielding SQL+pandas+spark framework to both build data and metric generation pipelines, and answer critical questions about system efficacy or counterfactual treatments
• Independently responsible for the entire lifecycle of projects or features including eng design, development, and deployment
• Works well with other stakeholders - has worked with cross-functional teams to drive projects over the finish-line
• Machine learning academic background (Bachelor's degree in Computer Science or related fields)

Desirable

• Abnormal Security is looking for a Senior Machine Learning Engineer to join the Message Detection Decisioning 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
• That’s what makes our novel behavioral-based approach so…Abnormal
• Abnormal has constantly been named as one of the top cybersecurity startups and our behavioral AI system has helped us win various cybersecurity accolades resulting in being trusted to protect more than 8% of the Fortune 1000 ( and ever growing )
• In a landscape where a single successful attack can lead to financial losses of millions of dollars, the Message Detection Decisioning team plays the central role of building an extremely precise Detection Engine that can operate on hundreds of millions of messages at milliseconds latency
• Every email ingested by Abnormal flows through the workflow owned by the Detection Decisioning team which applies hundreds of signals and detectors on a message based on the message and user context
• The system then computes the final overall decision for the system and consequently chronicles attribution to drive various offline and online metrics such as offline precision, online precision, online False Negative Rate etc
• 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 high precision systems
• The team builds discriminative signals at various levels including message level (eg Presence of particular phrases), sender-level (eg.frequency of sender) and recipient level (eg.likelihood of receiving a safe message) which forms the foundation to create highly accurate heuristic and model based detectors)
• Additionally to maintain an overall high precise detection system, the team innovates on software systems and processes which can be quickly adapted to solve trends seen in the short term as well as generalize well in the longer term
• This role would also have an opportunity to have a huge impact on the overall charter, direction and growth of the team
• The Senior Machine Learning Engineer would be involved in understanding the most pressing customer problems in the domain of false positives and build out the associated technical roadmap to continuously operate our detection decisioning system at an extremely high precision
• What you will do
• Design and implement systems that combine rules, models, feature engineering, and business and product inputs into an email detection product
• Identify and recommend new features groups or ML model approaches that can significantly improve detection efficacy for a product
• Work with infrastructure & systems engineers to productionize signals to feed into the detection system
• Understand features that distinguish safe emails from email attacks, and how our detector stack enables us to catch them
• Be the expert in main detection pipelines and decision data flow to be able to drive debugging in systematic degradations caused by bad detectors
• Writes code with testability, readability, edge cases, and errors in mind
• Train models on well-defined datasets to improve model efficacy on specialized attacks
• Actively monitor and improve False Positive rates and efficacy rates for our message detection product attack categories, through feature engineering, rules and ML modeling
• Analyze False Negative and False Posi datasets to categorize capability gaps and recommend short term feature and rule ideas to improve our detection efficacy
• Contribute in other areas of the stack: building and debugging data pipelines, or presenting results back to customers in our tools when the occasion arises
• Lead the team’s medium and long term roadmap and drive planning and execution strategy for the pod
• Coach and mentor junior engineers to uplevel their code quality and ML effectiveness by providing quality code reviews and design reviews
• Participate in building a world-class detection engine across all layers - data quality, feature engineering, model development, experimentation and operation
• This position is not:
• A role focused on optimizing existing machine learning models
• A research-oriented role that's two-steps removed from the product or customer
• A statistics/data science meets ML role

• Initial Application
• Designed to get you in and moving through our assessment process, we will ask for the basics such as name, email, resume, etc
• Recruiter Interview
• If we’re moving forward, the next step is a 30-25 minute chat with one of our recruiters
• The recruiter will give a general overview of the role and dive a bit deeper into your experience and background, specifically as it relates to the role you applied for
• This is a great time to ask any general questions about the role, the team, and our company
• Hiring Manager Interview
• If our recruiter thinks your background could be a good fit, you’ll move forward to meet with the hiring manager
• This will be a more in-depth conversation about your background and skillset to see if there is a mutual good fit
• This is a great space to ask more specific questions about the role and manager expectations
• Skills Assessment
• If you’re applying for a technical role, you can expect this to be a part of your process
• These are usually coding challenges designed to give you a sense of the work you’d be doing, and for us to see how you problem-solve
• Final Interviews
• The last stage in our process is a series of 1:1 Zoom interviews with a handful of other folks on our team that you’d be working with
• This varies from role to role, but typically we’ll have you meet with 3-5 team members
• These are separate, stacked interviews– we don’t do panel interviews
• We try to get all of these scheduled on the same day, but if your schedule doesn’t allow for that, our recruiting ops team will work closely with you to coordinate a schedule that works for you