Description
Job Summary:
We are seeking a passionate and visionary Generative AI Engineer to advise financial sector clients, directly impacting service quality.
Key Highlights:
1. Join a leading global professional services network in Peru.
2. Advise financial sector clients in a high-impact role.
3. Develop and deploy innovative Generative AI solutions.
Location: Lima
Other locations: Primary Location Only
Salary: Competitive
Date: Jul 14, 2026
**Job description**
-------------------
Requisition ID: 1726623
At EY, we are looking for passionate and visionary professionals like you who are ready to join us in building a better business world. As part of a global professional services network, you would join over 390,000 professionals across 150 countries and 700 offices worldwide. Our local practice comprises more than 2,500 professionals across four cities and serves the country’s largest economic groups, making us Peru’s leading professional services firm. Our goal is to develop exceptional leaders while valuing diversity and inclusion. Join EY—and together, let’s build a better business world!
**FSO:**
As a member of our service line, you will provide advisory services to our financial sector clients. You will therefore be an integral part of the team—meaning everything you do will have a direct impact on the quality of service we deliver to our clients, helping them assess and optimize their businesses. Additionally, you will contribute to our account-focused growth strategy, centered on our clients’ needs, relevant topics, and competency-driven solutions. This is what differentiates EY in the advisory market.
**Generative AI Engineer:**
**Requirements**
* Bachelor’s degree in Systems Engineering, Computer Science, Software Engineering, or related field.
* 5+ years of experience, including at least 1 year in Generative AI projects and AWS/Azure.
* Experience using AI services on AWS/Azure, LangChain/LangGraph, vector databases, integration with foundational LLMs, and Python.
* Intermediate English proficiency.
**Responsibilities**
* Development of Generative AI Agents using LangChain and LangGraph libraries.
* Deployment of agents and business logic on AWS, using Lambda for serverless processes and Amazon ECS for containerized services or longer-running workloads.
* Management of conversational memory mechanisms, state persistence, session management, and knowledge retrieval via RAG architectures.
* Proficiency with Vector Databases: Qdrant, Pinecone, PG Vector, and/or S3 Vectors.
* Proficiency with AWS AI Services: Amazon Textract, Amazon Bedrock, and Knowledge Bases for Amazon Bedrock—or their Azure equivalents.
* Integration with state-of-the-art foundational models such as Claude Opus, Claude Sonnet, Claude Haiku, GPT\-5, or equivalent models available through Amazon Bedrock, Azure AI Foundry, or other enterprise-grade services.