Solution Analyst Ii- AI

JPMorgan Chase JPMorgan Chase · Banking · GLASGOW, LANARKSHIRE, United Kingdom · Asset & Wealth Management

This role focuses on integrating large language models (LLMs) into enterprise workflows, specifically within the Global Private Bank Tech Investments team at JPMorgan Chase. The Solutions Analyst II will bridge the gap between business stakeholders and developers, translating requirements into technical solutions. Key responsibilities include extracting insights from data, collaborating on architecture designs, managing project dependencies, and promoting continuous improvement. The role requires experience in solutions analysis, data fluency, and technical curiosity. Preferred qualifications include experience with LLM APIs, RAG patterns, prompt engineering, evaluation, risk controls, and LLM orchestration frameworks like LangChain.

What you'd actually do

  1. Contribute to data-driven decision-making by extracting insights from large, diverse data sets and applying data analytics techniques
  2. Collaborate with cross-functional teams to provide input on architecture designs and operating systems, ensuring alignment with business strategy and technical solutions
  3. Assist in managing project dependencies and change control by demonstrating adaptability and leading through change in a fast-paced environment
  4. Promote continuous improvement initiatives by identifying opportunities for process enhancements and applying knowledge of principles and practices within the Solutions Analysis field
  5. Guide the work of others, ensuring timely completion and adherence to established principles and practices

Skills

Required

  • solutions analysis
  • eliciting and documenting business and data flow requirements
  • data fluency
  • data extraction
  • data interpretation
  • making data-informed decisions
  • technical fluency
  • data visualization
  • analytics
  • vendor product understanding
  • vendor relations management
  • written communication skills

Nice to have

  • integrating large language models into enterprise workflows via APIs
  • retrieval-augmented generation patterns
  • embeddings
  • vector stores
  • grounding strategies to reduce hallucinations
  • prompt engineering
  • evaluation
  • acceptance criteria for non-deterministic outputs
  • human-in-the-loop review design
  • risk controls for model failures
  • LLM orchestration frameworks
  • LangChain
  • enterprise platforms
  • Agile delivery
  • Scrum
  • Kanban
  • JIRA
  • Confluence
  • Python
  • SQL
  • REST APIs
  • data visualization tools

What the JD emphasized

  • integrating large language models into enterprise workflows via APIs
  • retrieval-augmented generation patterns
  • grounding strategies to reduce hallucinations
  • prompt engineering and evaluation
  • acceptance criteria for non-deterministic outputs
  • risk controls for model failures

Other signals

  • integrating large language models into enterprise workflows via APIs
  • retrieval-augmented generation patterns
  • grounding strategies to reduce hallucinations
  • prompt engineering and evaluation
  • risk controls for model failures
  • LLM orchestration frameworks