Skip to content
View simonamador's full-sized avatar

Block or report simonamador

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
simonamador/README.md

Simón Amador

AI Engineer @ Bagó

AI Engineer | Biomedical AI Researcher | Builder

Building reliable AI systems in healthcare, from pharmaceutical operations to biomedical research.

WebsiteLinkedInGoogle ScholarGitHubX/Twitter

Profile views


About Me

I build AI systems in healthcare at the intersection of production engineering, research, and product delivery.

At Laboratorios Bagó del Perú, I lead AI initiatives for pharmaceutical commercial and medical workflows. My work spans agentic systems, RAG, evaluation, analytics, deployment, and cross-functional delivery. These systems serve 120+ users, with a clinical RAG platform handling 7,000+ queries per week.

My biomedical AI research focuses on generative modeling and anomaly detection for fetal MRI. I contributed to work published in NeuroImage and presented at ISMRM, OHBM, and MIT-MGB AI Cures.


Current Focus

  • Taypi Observatory: local-first workbench for discovering, executing, auditing, and replaying MCP and A2A interactions
  • MRIxFields 2026: cross-field MRI translation and harmonization for the MICCAI challenge
  • Production agentic and RAG systems for pharmaceutical workflows
  • Graduate study, research collaboration, and innovation leadership opportunities

Featured Projects

A local-first visual workbench for MCP and A2A interactions, with approval gates, append-only traces, replay, protocol inspection, reliability reports, and deterministic failure injection.

Deep generative normative modeling for structural and developmental anomaly detection in fetal brain MRI.

A sanitized architecture case study for an enterprise multi-agent system using Python, Flask, Oracle SQL, RAG, and commercial LLM APIs.

Synthetic identity infrastructure for facial consistency using embeddings, geometric landmarks, and longitudinal drift tracking.


Publications

Journal Article

Conference Presentations

  • Conditional deep generative normative modeling for structural and developmental anomaly detection in the fetal brain — ISMRM, 2025
  • Deep generative anomaly detection for structural anomalies in fetal brain with ventriculomegaly — OHBM, 2024
  • Covariate-conditioned fetal MRI anomaly detection — MIT-MGB AI Cures, 2024

Technical Stack

Languages: Python SQL Bash
Frameworks: PyTorch FastAPI Flask Next.js scikit-learn
Infrastructure: Docker REST APIs SSE CI/CD Oracle SQL
AI: LLMs RAG Agentic Systems Evaluation Generative Models Medical Imaging


Selected Impact

  • Built AI systems used by 120+ internal users
  • Scaled a clinical RAG platform to 7,000+ queries per week
  • Led technical delivery across engineers, business teams, and external specialists
  • Co-authored peer-reviewed research in NeuroImage
  • Organized a two-day AI hackathon with 70+ participants and 17 evaluated projects

Open To

  • Fully funded graduate study
  • Research collaborations
  • Applied AI and innovation leadership roles
  • Health AI, biotechnology, and agentic-systems opportunities
  • Focused technical consulting engagements

Contact


Building AI systems that translate research into real-world impact.

Pinned Loading

  1. fetal-mri-anomaly-detection fetal-mri-anomaly-detection Public

    Unsupervised learning framework for localizing structural brain anomalies in fetal MRI. VAE-based generative models trained per anatomical view with L2/SSIM/combined losses; β-VAE and gestational-a…

    Python 3

  2. personalab personalab Public

    Production-grade synthetic identity infrastructure that enforces facial consistency using embeddings, geometric landmarks, and longitudinal drift tracking.

    Python 1

  3. enterprise-llm-agent-architecture enterprise-llm-agent-architecture Public

    Architecture and design documentation for Yachai, a production multi-agent LLM system on WhatsApp serving 120 pharmaceutical sales reps with 4,000+ weekly queries. Custom orchestration over Flask, …

    Mermaid