• Job Description

  Req#: 20143
  Why N-able
  
  
  At N-able, we’re not just helping businesses be secure —we’re redefining what it means to be cyber resilient. Our end-to-end platform blends AI-powered capabilities and flexible tech stacks, so customers can manage, secure, and recover with confidence. But the real power behind it all? Our people. We’re a global crew of N-ablites, who love solving complex problems, sharing knowledge, and delivering solutions that actually make a difference. If you're into meaningful work, fast growth, and a team that’s got your back, you’ll be surrounded by people who believe in what they do—and in you.
  If you are an affable and talented data practitioner with excellent attention to detail who enjoys a flexible, fast-paced work environment, the N-able Data Science team is the place for you! We are a cloud-native, machine learning-empowered, one-stop cybersecurity solution that combines event monitoring, threat detection, and incident response. Our clients range from small regional financial institutions to multinational corporations.
  The Data Science team collaborates with the broader Engineering organization to automate the ingestion of security logs into the cloud and builds machine learning solutions for empowering IT security. These applications have immediate impact on clients, allowing effective monitoring of billions of log messages and highly informative alerts on events that warrant further investigation. We build intrusion detection systems that don’t just match patterns — they reason about behavior. Our models learn to catch subtle and novel threats by understanding the statistical, geometric, and semantic structure of network activity, not just replaying yesterday’s rules. You’ll be working on the front lines of applied machine learning for cybersecurity, where your models will make real decisions that stop real intrusions.
  Note: this role is open to candidates who are local to DC, MD, and VA.
  
  What You'll Do
  
  
  Your models will help detect live threats — not just optimize a metric. You’ll see your ideas go from whiteboard to production in weeks and months, not years. We value creative solutions, not just the “standard” way of doing things.
  Our ideal teammate will bring strong mathematical probability and linear algebra intuition for building anomaly detection models that catch rare, novel, and unexpected behaviors in massive streams of security events. Prior experience in cybersecurity is not needed — if you can think rigorously about uncertainty, high-dimensional geometry, and how to represent data for modeling, we will teach you the threat landscape.
  • Design, prototype, and deploy statistical and machine learning models for real-time anomaly detection in intrusion detection systems
  • Apply Bayesian inference, probabilistic modeling, and dimensionality reduction to detect novel attack patterns
  • Work with large-scale, high-dimensional event data (e.g., authentication logs, DNS, process creation)
  • Explore embeddings and representation learning to capture behavioral meaning in raw security events
  • Collaborate with Senior Engineers and threat hunters to deploy models at scale, evaluate model output, and improve detection fidelity
  • Own your work from concept to deployment — your models will ship and be used in production
  
  What You'll Bring
  
  
  • Strong understanding of probability theory and statistical inference
  • Comfort with linear algebra concepts: vector spaces, projections, eigenvalues/eigenvectors, matrix factorization
  • Ability to reason through uncertainty and noise in real-world datasets
  • Proficiency in Python (NumPy, Pandas, scikit-learn, or similar)
  • Problem-solving mindset — able to design approaches from first principles
  • Solve technical challenges specific to keeping machine learning applications compatible with the cloud architecture in place, being especially mindful of compute capacity optimization issues inherent in the platform
  • Utilize AWS services such as Lambda, Batch, and SageMaker as building blocks for the functions listed above
  • Write documentation and perform monitoring and performance evaluation on models under ownership and recommend development plans for future iterations and patches
  • Develop and maintain cloud-based platforms for safely testing new algorithms prior to deployment and for change management
  • Influence peers and leadership to advance promising solutions
  Bonus Skills
  • Experience with anomaly detection methods — statistical, unsupervised, or deep learning-based
  • Familiarity with representation learning, embeddings, or neural networks
  • Experience with PCA, t-SNE, UMAP, autoencoders, or other dimensionality reduction methods
  • Prior exposure to security data (SIEM, EDR, network logs, etc.)
  
  Purple Perks
  
  
  • Fully covered medical, dental and vision – for employee and eligible dependents!
  • Generous PTO and observed holidays
  • 2 Paid VoluNteer Days per year
  • Paid Parental Leave
  • 401(k) with company-match and Flexible Spending Accounts
  • Employee Stock Purchase Program
  • Free Lunch 2x per week at Collaboration Hubs
  • On-site gym access at select Collaboration Hubs
  • Wellness rewards
  • FuN-raising opportunities as part of our giving program
  • N-ablite Learning – custom learning experience as part of our investment in you
  
  About N-able
  
  
  At N-able , our mission is to protect businesses against evolving cyberthreats with an end-to-end cyber resilience platform to manage, secure, and recover. Our scalable technology infrastructure includes AI-powered capabilities, market-leading third-party integrations, and the flexibility to employ technologies of choice—to transform workflows and deliver critical security outcomes. Our partner-first approach combines our products with experts, training, and peer-led events that empower our customers to be secure, resilient, and successful.
  
  
  • Strong understanding of probability theory and statistical inference
  • Comfort with linear algebra concepts: vector spaces, projections, eigenvalues/eigenvectors, matrix factorization
  • Ability to reason through uncertainty and noise in real-world datasets
  • Proficiency in Python (NumPy, Pandas, scikit-learn, or similar)
  • Problem-solving mindset — able to design approaches from first principles
  • Solve technical challenges specific to keeping machine learning applications compatible with the cloud architecture in place, being especially mindful of compute capacity optimization issues inherent in the platform
  • Utilize AWS services such as Lambda, Batch, and SageMaker as building blocks for the functions listed above
  • Write documentation and perform monitoring and performance evaluation on models under ownership and recommend development plans for future iterations and patches
  • Develop and maintain cloud-based platforms for safely testing new algorithms prior to deployment and for change management
  • Influence peers and leadership to advance promising solutions
  Bonus Skills
  • Experience with anomaly detection methods — statistical, unsupervised, or deep learning-based
  • Familiarity with representation learning, embeddings, or neural networks
  • Experience with PCA, t-SNE, UMAP, autoencoders, or other dimensionality reduction methods
  • Prior exposure to security data (SIEM, EDR, network logs, etc.)
  
  
  Your models will help detect live threats — not just optimize a metric. You’ll see your ideas go from whiteboard to production in weeks and months, not years. We value creative solutions, not just the “standard” way of doing things.
  Our ideal teammate will bring strong mathematical probability and linear algebra intuition for building anomaly detection models that catch rare, novel, and unexpected behaviors in massive streams of security events. Prior experience in cybersecurity is not needed — if you can think rigorously about uncertainty, high-dimensional geometry, and how to represent data for modeling, we will teach you the threat landscape.
  • Design, prototype, and deploy statistical and machine learning models for real-time anomaly detection in intrusion detection systems
  • Apply Bayesian inference, probabilistic modeling, and dimensionality reduction to detect novel attack patterns
  • Work with large-scale, high-dimensional event data (e.g., authentication logs, DNS, process creation)
  • Explore embeddings and representation learning to capture behavioral meaning in raw security events
  • Collaborate with Senior Engineers and threat hunters to deploy models at scale, evaluate model output, and improve detection fidelity
  • Own your work from concept to deployment — your models will ship and be used in production

• About the company

  Software, resources, and tools for MSPs and IT departments with best-in-class Remote Monitoring & Management, Data Protection, and Security solutions.

Notice