John Paul Hernandez Alcala
John Paul Hernandez Alcala
I’m a bilingual data and cloud professional passionate about building secure, scalable systems that prioritize data confidentiality, integrity, and availability—especially in security-conscious and healthcare environments.
With certifications in AWS Data Engineer – Associate, AWS Solutions Architect – Associate, Security+, and Data Science, plus a Bachelor’s in Biomedical Engineering, I bring a cross-disciplinary mindset to every project.
At PathAI, I served as a Biomedical Data Manager II, where I:
Managed 500GB+ of image and metadata in AWS S3 for ELT pipelines supporting ML on Kubernetes
Automated validation workflows using Python and Bash, cutting processing time by 40%
Converted structured and semi-structured metadata with pandas, pushing to PostgreSQL in Parquet format
Scripted API interactions to streamline metadata uploads and reduce manual effort
Designed Metabase dashboards and SQL reports to monitor data integrity
Enforced fine-grained data access policies, including annotation and model training rights
Collaborated with QA on regulated clinical trial data, providing audit trails and locking GitHub branches for traceability
Whether I’m building pipelines, cleaning metadata, or enforcing compliance protocols, I thrive in cross-functional teams and environments where data quality and trust are non-negotiable.
Currently seeking fully remote roles in data engineering, cloud infrastructure, or AI-driven healthcare applications.
Check out his blog!
Construction of a deep neural network that trains on x-ray images of pediatric patients to identify whether or not they have pneumonia.
This project uses a data derived method for predicting which client type should be targeted for successful bank telemarketing. A presentation that investigates which client features affect marketing success rate and machine learning methods result in a high prediction accuracy and precision.
This project focuses on analyzing all games on superficial characteristics to see which could be predictive features for high download count.
This project gives a better understanding of house prices. A presentation that discusses at least two concrete features that highly influence housing prices is inlcuded. Findings from both the project and presentation are for people interested in maximizing their profit when selling their home.
Biomedical Data Manager PathAI, Boston, MA (Remote)
Data Engineering & Automation
● Managed 500GB+ of image and metadata in AWS S3 for ELT pipelines supporting machine learning in Kubernetes.
● Automated validation workflows with Python and Bash, cutting data processing time by 40%.
● Cleaned and associated structured/semi-structured metadata using pandas, converting to Parquet for upload into PostgreSQL.
● Scripted internal API interactions for efficient metadata uploads and updates, reducing manual effort and errors.
Data Access, Governance & Visualization
● Designed and enforced data access policies on PathAI’s platform to control image and metadata visibility, annotation rights, and ML training eligibility at the project, partner, always, or never level.
● Developed custom SQL queries and Metabase dashboards for internal reporting and data monitoring.
● Established secure sFTP data transfer protocols with internal and external teams, including pathologists and ML engineers.
Compliance & QA Collaboration
● Participated in regulated projects involving clinical trial data; collaborated with QA on root cause analysis and script validation, locking GitHub branches post-approval and providing SHA hashes to ensure audit traceability.
Neurophysiology Technologist Advanced Neuro Solutions (ANS), Amarillo, TX
● Provides intraoperative neurophysiological monitoring services to minimize neurological morbidity from surgeries
● Coordinates support of research to ensure the highest quality of data, leading to improved treatment
Clinical Allergy Specialist United Allergy Services (UAS), Amarillo, TX
● Articulated to patients the allergic response, the impact of common airborne and mold allergens, and the features and benefits of allergy skin testing and allergen immunotherapy
● Administered allergy skin tests, mixed allergen immunotherapy, and closely supervised treatment regime with the patient’s physician, nurse practitioner, or physician assistant
● Maintained inventory of all clinical supplies and led the fulfillment of the treatment goals and objectives of UAS in the designated clinic
MATLAB/LabVIEW Peer Mentor Texas A&M Biomedical Engineering Department, College Station, TX
● Exploited Raman and Brillouin spectroscopies in an innovative study of membrane rigidity
● Undergraduate Research Paper: http://hdl.handle.net/1969.1/177568
Undergraduate Researcher Advanced Spectroscopy Laboratory, College Station, TX
● Exploited Raman and Brillouin spectroscopies in an innovative study of membrane rigidity using in-house engineered Giant Unilamellar Vesicles and LabVIEW/.NET driven Thorlabs equipment
● Completed a 22-page undergraduate thesis which organized, analyzed, interpreted, and evaluated data
● Designed poster and presented research at the 2017 Texas A&M Student Research Week
Co-op Sterilization / Packaging Engineer Ethicon Inc. (Johnson & Johnson), San Angelo, TX
● Orchestrated business to business sales to source materials for suture production and sterilization processes
● Mitigated > 50 safety hazards or production issues that arose in the final packaging area and sterile/scrubs areas by communication with operators and craftsmen, quality system approved design, and development
● Wrote and filled out FDA compliant procedures and documents for the box separator and safety hazards/issues
CT/PET Radiological Medical Assistant Shared Medical Services, San Angelo, TX
● Provided customer service to ~10 patients/day and followed-up with no-show patients to ensure they were safe
● Started blood work on patients, educated patients briefly about the examination details, ran GE CT/PET scanner, ensured imaging focused on anatomy of interest with clarity, and filled out compliance paperwork