Consumer Behavior Modeler II

Bank of America Bank of America · Banking · Charlotte, NC

This role involves developing and implementing LLM-based solutions to enhance data analysis and insight generation within a financial institution. The candidate will leverage GenAI tools for querying large datasets and research/evaluate new models and methods, including prompting, fine-tuning, embeddings, evaluation harnesses, and guardrails, with a focus on building production-ready prototypes. Experience with LLMs, agent frameworks, and related technologies is required.

What you'd actually do

  1. Leverage GenAI based tools that take natural-language queries and return insights from large datasets
  2. Develop and implement LLM-based solutions to enhance data analysis and insight generation.
  3. Research and evaluate new models and methods (prompting, fine-tuning, embeddings, evaluation harnesses, and guardrails), and develop lightweight prototypes that can be productionized
  4. Demonstrates an advanced understanding of statistical modeling requirements expressed in a technical language and executes per a specified plan and timeline
  5. Analyzes and sanitizes large volumes of data

Skills

Required

  • Strong Python development skills with production-quality engineering practices.
  • Data and infrastructure experience: SQL, Starburst, Teradata, Hadoop, Linux/Unix, and cloud-native or distributed systems.
  • Experience with LLMs and agent frameworks: LangGraph, LangChain, OpenAI-compatible APIs, MCP, vLLM/Triton, multi-agent orchestration, and advanced prompt engineering.
  • Data Mining
  • Model Development
  • Artificial Intelligence/Machine Learning
  • Risk Modeling
  • Generative AI Models
  • Strong hands-on programming experience in Python and SQL.
  • Knowledge of Unix based environment and shell programming
  • Excellent analytical and problem-solving skills.

Nice to have

  • 3+ years of directly relevant experience
  • Advanced degree in engineering, computer science, statistics or another heavy quantitative discipline
  • Software engineering experience: FastAPI services, containerization, model deployment, and monitoring.
  • Oral Communications
  • Problem Solving
  • Technical Documentation
  • Analytical Thinking
  • Business Acumen
  • Innovative Thinking
  • Presentation Skills
  • Written Communications

What the JD emphasized

  • production-quality engineering practices
  • LLMs and agent frameworks
  • multi-agent orchestration
  • advanced prompt engineering

Other signals

  • Leverage GenAI based tools that take natural-language queries and return insights from large datasets
  • Develop and implement LLM-based solutions to enhance data analysis and insight generation.
  • Research and evaluate new models and methods (prompting, fine-tuning, embeddings, evaluation harnesses, and guardrails), and develop lightweight prototypes that can be productionized
  • Experience with LLMs and agent frameworks: LangGraph, LangChain, OpenAI-compatible APIs, MCP, vLLM/Triton, multi-agent orchestration, and advanced prompt engineering.