
Posted 11 days ago
Data Domain Architect Senior Associate - Agentic AI Evaluation & Annotation
JPMorgan Chase & Co.Data Domain Architect Senior Associate - Agentic AI Evaluation & Annotation
Requirements
Master's degree in CS, Data Science, or related field, 3+ years experience in AI evaluation or LLM applications, Experience with annotation schemas and rubrics, Hands-on Python experience, Knowledge of agentic AI concepts
Skills
PythonLLMAI
About the role
Responsibilities
- Define and operationalize evaluation metrics for agentic AI workflows, including task success, tool-use quality, and policy adherence.
- Design annotation schemas, rubrics, and taxonomies for evaluating agent trajectories across multi-turn and multi-tool scenarios.
- Build and maintain agent-specific gold sets, challenge sets, and regression suites to assess planning and grounding.
- Train, calibrate, and support annotators to ensure consistent application of labeling guidelines and quality expectations.
- Identify and report agent failure patterns such as incorrect planning, invalid arguments, or unsafe recommendations.
- Partner with ML engineers and product managers to align evaluation criteria with agent architecture and business requirements.
- Contribute to LLM-as-judge and automated evaluation workflows, including evaluator prompt design and rubric-based scoring.
Requirements
- Master’s degree in Computer Science, Data Science, AI/ML, or a related field.
- 3+ years of experience in AI evaluation, annotation programs, LLM applications, or agentic AI systems.
- Hands-on experience evaluating LLM-based systems, specifically regarding multi-step reasoning, planning, and tool use.
- Proven experience designing annotation schemas, evaluation rubrics, and labeling guidelines.
- Working knowledge of agentic AI concepts such as orchestration, tool invocation, and context management.
- Hands-on Python experience for data analysis, validation, and automation.
- Strong analytical and communication skills to translate complex agent behavior into measurable decisions.
Preferred Qualifications
- Experience evaluating autonomous or tool-using agents in production environments.
- Experience building agent evaluation benchmarks, trajectory datasets, or regression suites.
- Experience with agent observability, trace review, and evaluation pipelines.
- Knowledge of emerging agentic AI evaluation methods and best practices.
About the Company
JPMorganChase is a leading global financial services firm with a history spanning over 200 years. We provide innovative financial solutions to millions of consumers, small businesses, and prominent corporate and institutional clients. Our Consumer & Community Banking division leverages cutting-edge data and analytics to build competitive advantages and provide industry-leading digital solutions.
ScoutJobs Agent
Get matches like this delivered daily
Sign up free — we'll pull jobs that fit your CV from across the web and rank them for you.
Get started — it's freeData Domain Architect Senior Associate - Agentic AI Evaluation & Annotation
JPMorgan Chase & Co. · Bengaluru
