Senior Associate - Applied AI ML / Data Science

Testing Site - JPMC; Bengaluru; On-site; INR 1,000,000 - 1,500,000; Full time

Job summary

Testing Site - JPMC is seeking a senior data science leader to design, deploy, and operate production-grade ML solutions for AML and Financial Crime. You will own end-to-end model lifecycle, collaborate with FCC and Investigations, and drive scalable MLOps and governance practices.

The role emphasizes interpretable ML, explainability, and leadership to build a high-performing team focused on risk mitigation and regulatory alignment.

Qualifications

• Master’s or PhD in a quantitative discipline.
• Minimum of 6 years of hands‑on ML experience, with 3+ years in financial crime risk domains.
• Proven leadership delivering production ML for financial crime at enterprise scale.
• Advanced Python skills; strong experience with ML frameworks.
• Expertise in supervised learning, anomaly detection, and calibration/threshold optimization.
• Experience in model risk management, validation, and explainability for regulatory review.
• Excellent communication to translate complex models to stakeholders.

Responsibilities

• Lead the CCOR Financial Crime Data Science team to design, deploy, and operate production-grade ML solutions for AML monitoring.
• Drive research in supervised/unsupervised/semi-supervised learning and graph analytics to improve true positives and reduce false positives.
• Own end-to-end model lifecycle including framing, data sourcing, feature engineering, validation, and retraining.
• Maintain model risk management practices and governance across the lifecycle.
• Build and maintain robust MLOps pipelines, model registries, and automated monitoring.
• Collaborate with FCC, Investigations, Operations, and Technology to translate regulatory expectations into ML controls.
• Enhance investigator decisioning with interpretable ML and explainability techniques.

Skills

Python

ML frameworks

Leadership

Communication

Problem solving

Explainability methods

Education

Master's or PhD in quantitative field

Tools

TensorFlow/PyTorch

Feature stores

CI/CD for ML

Model governance tools

Job description

Job Responsibilities:

• Lead the CCOR Financial Crime Data Science team to design, deploy, and operate production-grade ML solutions across AML transaction monitoring use cases, with a strong focus on measurable risk mitigation and regulatory alignment.
• Drive research and applied innovation in supervised/unsupervised/semi‑supervised learning, graph/network analytics, anomaly detection, and weak supervision to improve true-positive rates, reduce false positives, and enhance investigator productivity.
• Own end-to-end model lifecycle: problem framing, data sourcing/controls, feature engineering (customer/behavioral/temporal/graph features), model development, validation, calibration/thresholding, bias/fairness checks, monitoring, and retraining.
• Maintain rigorous model risk management practices across Model lifecycle, partnering with Model Risk and Internal Audit.
• Build and maintain robust MLOps pipelines (CI/CD for ML), model registries, automated monitoring (data drift, concept drift, performance), and governance artifacts to ensure reliable, scalable production operations.
• Partner with Financial Crime Compliance (FCC), Investigations, Operations, and Technology to translate typologies, red flags, and regulatory expectations into defensible ML controls and measurable control effectiveness.
• Enhance investigator decisioning through interpretable ML: deploy explainability techniques (e.g., SHAP, LIME, counterfactuals), stable reason codes, and human-in-the-loop feedback loops to continuously improve model precision and usability.
• Mentor, hire, and develop a high-performing team of data scientists/ML engineers/analysts; promote a culture of scientific rigor, ethical AI, and continuous learning.
• Maintain a pragmatic view of GenAI/LLMs as complementary tools (e.g., narrative generation for cases, unstructured doc parsing) while prioritizing classical/statistical/graph ML methods for core detection efficacy.

Required Qualifications and Skills:

• Master’s or PhD in a quantitative discipline (Computer Science, Statistics, Mathematics, Economics, Operations Research, or related).
• Minimum of 6 years of hands‑on ML experience, with at least 3+ years in Financial Crime Compliance, AML, sanctions, fraud, or related risk domains; deep knowledge of regulatory expectations (e.g., AML program requirements, sanctions controls, model governance).
• Proven leadership delivering production ML for financial crime, including transaction monitoring models, risk scoring, anomaly detection, network/graph analytics, and/or investigator triage/prioritization at enterprise scale.
• Advanced Python skills; strong experience with ML frameworks.
• Expertise in supervised learning, anomaly detection, semi‑supervised learning, clustering, feature stores, and calibration/threshold optimization; familiarity with imbalanced learning and cost‑sensitive evaluation.
• Demonstrated experience in model risk management: documentation, validation, benchmarking/challenger models, backtesting, stability and drift analysis, champion/challenger governance, and explainability suitable for regulatory review.
• Excellent communication skills to translate and explain complex models with clear reason codes, and influence cross‑functional stakeholders and senior leadership.
• People leadership: recruiting, coaching, performance management, and fostering an inclusive, high‑accountability culture.