New: upload your resume and get matched to AI jobs. Free to start →

Principal Applied Scientist - Ads Ranking & Retrieval

India, Karnataka, Bangalore • Full-time

Posted 1mo ago

Job Location

India, Karnataka, Bangalore

Tech Stack

Remote Work Policy

On-site

Employment Type

Full-time

Categories

Machine Learning Engineer

About the job

The AI Economy Team at Microsoft is building the infrastructure to power how organizations ground, deploy, and scale AI applications. This role focuses on the Trust & Safety aspects of AI Economy access, developing systems to verify customer identities, detect coordinated account activity, and differentiate legitimate high usage from malicious exploitation. You will be responsible for framing these complex detection problems, building the necessary models, and deploying them into production environments to ensure secure and fair access to AI services.

Responsibilities

  • Lead AI Economy Trust & Safety projects from problem definition to production rollout and measurement.
  • Own identity resolution and clustering approaches for connecting accounts, tenants, and payment instruments to actors.
  • Develop and manage applicant-risk and ongoing account-risk models, including the evidence used for decisions.
  • Create detection methods to distinguish legitimate high-volume use from coordinated extraction and abuse.
  • Select and evaluate various machine learning approaches, including supervised learning, anomaly detection, graph methods, sequence models, and large language models.
  • Establish and maintain an evaluation framework for model quality, calibration, false-positive impact, drift, explainability, and adversarial robustness.
  • Collaborate with product and engineering teams to translate detection findings into product controls and coordinate with privacy, legal, and external stakeholders.

Requirements

  • Bachelor's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 6+ years of related experience, OR Master's Degree AND 4+ years of related experience, OR Doctorate AND 3+ years of related experience, OR equivalent experience.
  • Experience taking ambiguous, adversarial problems from framing to deployed systems, including evaluation.
  • Prior experience with know-your-customer, identity proofing, or payment risk in a self-serve or developer-facing product.
  • Experience reasoning about attacker economics and control costs for adversaries.
  • Depth across multiple modeling families, including graph and network methods, anomaly detection, sequence models, and large language models, with demonstrated success on adversarial data.
  • Experience building fraud, abuse, security, or risk detection systems delivered into a production environment.
  • Ability to meet Microsoft security screening requirements, including a Microsoft Cloud Background Check.