AI Engineer - Kyveria KI

Who are we?

We are Mexico's leading financial technology company, empowering over 100,000 clients to achieve their business goals. Our mission is to fuel the growth of small and medium-sized enterprises (SMEs) through innovative solutions—including financing, corporate credit cards, and payment systems. We partner with entrepreneurs to help them overcome challenges, transforming their businesses into true engines of economic growth while contributing to the development of our community, our country, and the planet.

About the Role

You will transform Kyveria—our internal QA tool—from its current workflow into a robust, production-grade AWS service. By leveraging Claude (Anthropic), you will automate the quality evaluation of customer interactions across multiple channels (chat, contact center, Salesforce). Your work will turn interaction grading into a reliable, measurable, and auditable capability, providing our Customer Experience (CX) team and external BPOs with daily, data-driven feedback to improve service quality.

Key Responsibilities

Platform Migration: Migrate the current workflow (n8n/spreadsheets) into a scalable AWS production service, establishing separate development and production environments.

Data Integration: Build direct integrations to read customer interactions straight from their sources (Salesforce Service Cloud, Amazon Connect, chat) and ensure proper data retention.

AI Quality Evaluation: Design and operate evaluation pipelines using Claude, managing versioned prompts and quality rubrics while tracking cost and model version per evaluation.

Evals & Continuous Improvement: Build automated evaluations (evals) to measure the AI's consistency against human reviewers, iterating on prompts and rubrics based on hard data.

Business Collaboration: Work daily with the CX team and BPOs to generate actionable feedback per agent, explain AI grading limits, and translate user needs into technical improvements.

Required Profile

Artificial Intelligence: Technical mastery of Claude and advanced Prompt Engineering, specifically in text extraction, classification, and grading flows. Experience writing LLM evaluations.

Software Engineering: 3+ years of backend development experience in production environments using Python or TypeScript.

Data & Integration: Strong SQL skills, basic data modeling, and experience integrating with external APIs and data sources.

Cloud & DevOps: Experience with Git, code reviews, CI/CD, and working with AWS at a developer level (EC2, S3, Secrets Manager).

Desirable: Experience with Salesforce Service Cloud, Amazon Connect, n8n, Postgres, and a background in Contact Center or QA operations.

Value Proposition

Impact at Scale: Build solutions that solve real financial challenges for Mexican businesses.

Cutting-Edge Innovation: Lead the integration of Generative AI in high-impact regulated products.

Culture of Excellence: Join a team focused on critical thinking, agile execution, and a strong sense of ownership.

Operational Flexibility: A results-oriented work model designed to maximize your productivity and professional development.