AI
Engineer
+
Researcher
I research how to make long urban video searchable — vision-language models, agentic retrieval, visual analytics. Then I ship it: Django and DRF services, React front-ends, Docker and Kubernetes.
Peer-reviewed research
Publications
Computer Graphics Forum, vol. 45, no. 3 (Proc. EuroVis 2026)
UrbanClipAtlas: A Visual Analytics Framework for Event and Scene Retrieval in Urban Videos
Joel Perca, Luis Sante Taipe, Juanpablo Heredia, João Rulff, Claudio Silva, Jorge Poco
A visual analytics system for exploring long urban videos recorded at street intersections. It segments recordings into clips, describes them with a vision-language model and indexes them for semantic retrieval, combining retrieval-augmented generation with taxonomy-aware entity extraction and video grounding. A knowledge graph aligns the language model output with detected objects and trajectories, so every answer can be visually grounded and verified. Evaluated on the StreetAware dataset through case studies on hazardous scenarios and pedestrian crossing dynamics.
Presented at EuroVis 2026 — Nottingham, UK — June 2026
First author · Published
Computers & Graphics (Proc. SIBGRAPI 2025)
STRive: An association rule-based system for the exploration of spatiotemporal categorical data
Mauro Diaz, Luis Sante Taipe, Joel Perca, João Da Silva, Nivan Ferreira, Jorge Poco
A system for mining and exploring association rules over spatiotemporal categorical data. It pairs rule generation and rule clustering with an interactive interface offering two analysis modes — one at the cluster level, one at the individual rule level — connected through coordinated views. Demonstrated through case studies on fatal vehicle accidents and urban crime.
Measured outcomes
Impact
90%
Reduced time spent on key operational processes by 90% through Python automation.
Multi-system
Integrated CRM/ERP, LMS, and messaging channels into end-to-end workflows.
Scalable
Microservices and CI/CD architecture for reliable, scalable deployments.
Systems I have shipped
Featured projects
Product/Platform
Podchy
Kubernetes-based Code as a Service platform to run code via web UI.
- Microservices-based architecture with scaling criteria.
- Deployment on Google Cloud Platform with CI/CD.
System
Lamport
Attendance system (Django/React/TypeScript) for a conference; team lead and deployment.
- Microservices-based architecture with scaling criteria.
- Deployment on Google Cloud Platform with CI/CD.
Where I have worked
Experience
Tech Lead · Grupo CEU Perú
Lima, PE
Led the digital transformation area: project delivery, support and evolution of CRM/ERP, automation, and microservices-based architecture.
- Technical leadership in automations (conversational chatbot for WhatsApp support).
- Infrastructure and architecture management (website, LMS, CRM, ERP, automations).
RPA Developer · NTT Data Europe & Latam
Trujillo/Arequipa, PE
Process automation with Microsoft Power Platform and SAP iRPA; supported apps built with Power Apps/Dataverse and flows in Power Automate.
- Business process automation (no/low-code).
- Internal support and training on tools.
Software Engineer · Grupo CEU Perú
Lima, PE
Process automation and systems integration; implemented ERP/CRM with Django REST Framework and React.
- ERP/CRM implementation: Django REST Framework, React, Docker Compose.
- Cleaning/processing historical data for prospect segmentation.
Software Developer · Bitmaker
Arequipa, PE
Contributed to the open-source project 'estela' (DRF backend + React/TS frontend); built endpoints and performed code reviews; improved the CLI for file uploads.
- Implemented REST APIs and performed code reviews.
- Optimized estela-cli for better uploads on slow networks.
Open to collaboration
Contact
Research collaborations, engineering work, or a question about the papers.
joelperca.vc@gmail.com