AI Backend Engineer

Payments & Reconciliation

Location: Flexible

Department: Engineering

Reports to: CTO

About the Company

They are building a finance-first All-In-One Operating System for Education in Latin America — a unified platform integrating payments, billing, collections, student information systems, academic workflows, communication, and financial operations.

They currently serve over 1,000 schools across Mexico, Colombia, and Ecuador, supporting hundreds of thousands of families with a modern, reliable experience for parents, students, teachers, and administrators.

Backed by leading global fintech and edtech investors, their mission is to enable schools to operate with clarity, accuracy, and confidence through technology and AI-driven automation.

As the platform scales across LATAM, AI is a central pillar of the product and engineering strategy.

Role Overview

They are seeking an AI Engineer to design, build, and deploy AI-native systems that drive automation, intelligence, and operational excellence across their products: Payments, Collections, SIS, Billing, Factoring, and Credit.

You will operate at the intersection of LLM engineering, backend development, data workflows, and agentic automation, transforming manual and fragmented processes into scalable AI-powered systems used by thousands of schools and hundreds of thousands of families.

This role combines backend engineering, LLM orchestration, RAG pipelines, evaluators, agents, and GenAI infrastructure. You will work closely with Product, Data, Backend, and Operations teams to convert ambiguous business problems into production AI features that directly impact real financial outcomes.

This is a high-impact, high-ownership position in a fast-paced environment — ideal for someone who wants to build production-ready AI systems, not just prototypes.

What You’ll Lead

1. Build & Deploy AI Systems

   • Design and build AI-powered microservices (Python/FastAPI) for inference and decision automation.

   • Implement LLM workflows using LangChain, LangGraph, CrewAI, AutoGen, or MCP-based architectures.

   • Build RAG pipelines: ingestion, chunking, embeddings, retrieval, re-ranking.

   • Integrate AI features into core products (Payments, Collections, Billing, SIS).

2. AI Agents & Automation

   • Build agentic workflows for data reconciliation, anomaly detection, financial validation, compliance checks, and school-specific automations.

   • Design structured tool-calling, guardrails, and self-correction loops.

   • Implement event-driven AI pipelines connected to Kafka/SQS.

3. Retrieval, Data & Evaluation

   • Implement and optimize vector stores (pgvector, FAISS, Weaviate, Milvus).

   • Create evaluation dashboards and automated evals to benchmark AI reliability.

   • Build observability around prompts, costs, latencies, and error handling.

4. Backend, APIs & Systems Engineering

   • Build scalable APIs integrating AI models with the existing microservice ecosystem.

   • Deploy AI services on AWS using ECS, Lambda, SQS, Aurora, Redis, S3.

   • Ensure security, compliance, PII protection, and safe AI usage.

5. Product & Cross-Functional Collaboration

   • Partner with Product and Operations to translate business needs into AI features.

   • Convert prototypes into robust, production-ready services.

   • Work with Data Engineering to power training, feature engineering, and retrieval.

Required Qualifications

• 4+ years of experience in software engineering, data engineering, or ML engineering.

• 1+ year hands-on building LLM-powered systems (agents, RAG, pipelines, evaluators).

• Strong Python skills; experience with FastAPI preferred.

• Experience with LangChain, LangGraph, CrewAI, AutoGen, or MCP.

• Experience with vector DBs: FAISS, Milvus, pgvector, Pinecone.

• Experience calling/integrating OpenAI, Anthropic, Mistral, Gemini, Groq, or similar APIs.

• Familiarity with SQL and relational models (PostgreSQL/Aurora).

• Strong understanding of REST/gRPC API design.

• High ownership and bias for action.

• Ability to take ambiguous problem statements and ship solutions fast.

• Strong communication and collaboration skills.

• Comfortable in a fast-paced, startup environment.

• Full professional proficiency in Spanish and English (written & spoken).

Preferred Qualifications

Experience with:

• RAG optimization (hybrid search, re-ranking).

• AI observability (OpenTelemetry, Evidently, custom evals).

• Redis, Kafka, SQS, event-driven architectures.

• Prompt engineering & safety pipelines.

• Prior experience in fintech, payments, or high-integrity systems.

Responsibilities may vary, but can include

• Build and own AI microservices end-to-end.

• Design and implement agentic workflows for automation across billing, reconciliation, collections, SIS.

• Evaluate and tune LLM performance, latency, cost, reliability.

• Implement guardrails, safety policies, and PII protection.

• Collaborate in code reviews, architecture discussions, and roadmap planning.

• Document workflows, APIs, prompts, evals, and data flows.

Location

Flexible

Travel: Occasional travel to Mexico City for team onsite sessions

Strong engineers ready to own production AI systems that power financial operations at scale should apply.