Help shape how trustworthy, AI-powered analytics scales across a complex business at JPMorganChase. You will build reusable foundations—semantic standards, shared components, and evaluation frameworks—that make analytics measurable, governed, and reliable. This role blends hands-on engineering with close partnership across data, analytics, and business stakeholders. If you like turning expert analyst workflows into repeatable, testable capabilities, this role is built for you.

Job summary

As an AI Analytics Enablement Associate in Chase Card Data and Analytics, you will help build the foundation for accurate, governed, and scalable AI-driven analytics. You will translate analyst expertise and historical query patterns into reusable assets that are easy to find, validate, and improve over time. You will partner with data owners and domain experts to establish human-approved definitions as a source of truth, with AI assisting in drafting and acceleration. You will design and operate evaluation and monitoring mechanisms so quality is measurable and releases are controlled. You will work directly with business stakeholders to gather feedback and convert it into clear accuracy and reliability improvements.

This is an enablement and platform role focused on building standards, reusable tooling, and operating mechanisms that help teams use AI safely and consistently. You will contribute to shared libraries of skills, procedures, and analytical harnesses that make AI usage repeatable across workflows. Success is measured through adoption, analyst efficiency gains, evaluation performance, semantic compliance, and adherence to automated quality gates. 

Job responsibilities

• Build and maintain version-controlled documentation and reusable analytical patterns from historical queries and analyst knowledge.
• Partner with data owners and domain experts to define and govern a semantic layer with human-approved definitions.
• Create and maintain versioned libraries of reusable skills and procedures, including inputs, outputs, canonical filters, and business rules.
• Define validation checks, edge cases, and performance expectations for reusable analytics capabilities.
• Contribute to standardized reporting and dashboard-generation tools and shared delivery standards.
• Build and operate benchmark test sets, regression suites, and automated evaluations for analytics quality.
• Define release-gating thresholds and rollback criteria to support controlled changes and reliable deployment.
• Convert analytics standards into auditable mechanisms such as linting rules, unit tests, and CI/CD quality gates.
• Instrument telemetry and monitoring dashboards to track usage, quality, and reliability over time.
• Support experimentation and measurement for natural-language analytics interfaces, including accuracy and semantic compliance.
• Translate stakeholder feedback into measurable improvements to platform quality and user outcomes.

Required qualifications, capabilities, and skills

• Proficiency in Python for data manipulation, scripting, and automation (for example, pandas).
• Strong SQL skills, including writing, optimizing, and debugging complex queries with joins, aggregations, and window functions.
• Knowledge of software engineering fundamentals, including data structures, algorithms, and clean coding practices.
• Working proficiency with Git-based version control, including code review workflows.
• Experience writing tests and implementing automated quality checks in a delivery pipeline (CI/CD).
• Experience building data or analytics tooling in modern data-warehouse environments.
• Ability to define business rules and validation logic and convert them into repeatable, testable mechanisms.
• Ability to partner effectively with data, domain, and analytics stakeholders to define measurable requirements and outcomes.
• Hands-on experience using AI coding assistants (for example, GitHub Copilot or similar tools) to accelerate development and testing.

Preferred qualifications, capabilities, and skills

• Familiarity with large language models and modern application frameworks (for example, LangChain or similar).
• Experience building retrieval-augmented generation workflows and managing retrieval quality for analytics use cases.
• Exposure to semantic layer patterns and governed metrics/definitions in analytics platforms.
• Experience designing evaluation frameworks for text-to-SQL or conversational analytics (accuracy, faithfulness, groundedness).
• Experience implementing observability patterns for analytics products (telemetry, monitoring, error analysis workflows).
• Experience building reusable “harness” tooling or standardized workflows that scale across teams.