Senior AI Data Engineer — Remote (Colombia)

Caseware; Medellín; Presencial; COP 140.000.000 - 210.000.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Permanent contract

Prepaid Medicine

Life insurance

Internet allowance

Home office stipend

Competitive compensation

100% remote work

Training budget

Descripción de la vacante

Caseware is seeking a Senior Software Developer – AI Data Engineer to define, design, and implement the data architecture powering Caseware’s AI platform. You will lead scalable ingestion, processing, storage, and retrieval for structured, unstructured, and multimodal data, establishing data models, governance, and platform capabilities.

Fully remote in Colombia, you will collaborate with AI, platform, and product teams to evolve reference architectures, ensure data quality, lineage and

Formación

• Strong software engineering fundamentals with end-to-end ownership.
• Production experience with distributed systems and async workflows.
• Hands-on data pipelines for AI systems, including embeddings & retrieval.
• Experience with AI data infra: vector databases, search, graph storage.
• Experience with retrieval systems (RAG) and hybrid search.
• Experience with agent frameworks and orchestration of tool-using AI systems.
• Production operations: monitoring, incident response, continuous improvement.
• Cloud experience on AWS with storage, messaging, and orchestration.
• Infra as code experience, CDK preferred; Terraform acceptable.
• Strong collaboration, mentorship, and English communication skills.

Responsabilidades

• Design and implement reliable, scalable data ingestion and integration pipelines for structured, semi-structured, unstructured, and multimodal data, ensuring data is AI-ready, governed, secure, and observable.
• Build and scale retrieval infrastructure, including vector storage, embedding pipelines, hybrid search, and graph-based knowledge representations, while optimizing data modeling for retrieval quality.
• Develop and operate agent memory systems and pipelines for AI system signals to support observability and continuous improvement.
• Apply data quality, validation, monitoring, and testing frameworks in production pipelines, ensuring governance, access control, lineage, and security standards are met.
• Monitor, troubleshoot, and optimize AI data pipelines and retrieval workflows for reliability, performance, and cost with strong observability.
• Design and support evaluation workflows for AI systems, enabling offline testing and benchmarking of retrieval and agent performance.
• Lead pragmatic platform evolution by defining contracts between AI services and data systems, reducing coupling, and improving developer experience.

Conocimientos

Data architecture

Distributed systems

Python

TypeScript

AI pipelines

Vector search

AWS Cloud

Observability

Data governance

Team leadership

English fluency

Herramientas

NestJS

Python

AWS OpenSearch Serverless

DynamoDB

S3

LangFuse

LangSmith

GitHub Actions

Terraform

CDK

Descripción del empleo

Caseware is seeking a Senior Software Developer – AI Data Engineer to define, design, and implement the data architecture powering Caseware’s AI platform. You will lead scalable ingestion, processing, storage, and retrieval for structured, unstructured, and multimodal data, establishing data models, governance, and platform capabilities.

Fully remote in Colombia, you will collaborate with AI, platform, and product teams to evolve reference architectures, ensure data quality, lineage and