walid abu al-afia
Building the systems
behind the science.
Computational Engineer II
St. Jude Children's Research Hospital
I build and operate AI infrastructure that turns research intent into running pipelines. Production MCP servers, agent harnesses, and the HPC systems behind them.
Memphis, TN From Amman, Jordan M.S. student, UT Austin
Connected by design
The whole stack.
From cluster compute to research pipelines, connected by an agent harness and production MCP servers.
A little perspective.
Infrastructure at St. JudeCPU Cores
55,000+
across 6 clusters
GPUs
2,500+
managed & allocated
Cluster Environments
6
HPC & SCCE clusters
Data Migrated
45 PB
cryo-EM/ET data · over 8 months
Always building.
The full story ↗Right now
Current roles
Current
Computational Engineer II
St. Jude Children's Research Hospital
May 2024 – Present
Current
IS Internship Coordinator
St. Jude Children's Research Hospital
May 2023 – Present
Current
M.S. Computer Science
UT Austin
Aug 2025 – Dec 2028 (expected)
Along the way
Milestones2025–26 Migrated 45 PB of imaging data over 8 months, within the 11 months to September 2026
2026 St. Jude Living Our Values Honoree
2025 / 08 Started M.S. Computer Science at UT Austin
2025 / 06 NVIDIA Certified Associate: AI Infrastructure & Operations
2024 / 05 Started Computational Engineer II role
2023 / 10 Published at IEEE/RSJ IROS 2023
2023 / 05 Promoted to Computational Engineer I
2023 / 05 Graduated Rhodes College — Magna Cum Laude
2022 / 09 Started HPC Engineering Student role at St. Jude
2022 / 06 HPC Research Computing Intern at St. Jude
Experience
A career in computing
Work history
Select a role to read more
JOBID
Organization
Role
Status
Dates
NODES
Highlights
- Architected and leads Pipeline Skill Zoo, taking an MCP automation platform from proof of concept to production. Owns daily iteration and new pipeline servers for natural-language execution of research pipelines on LSF/Slurm clusters
- Converted research pipelines into dedicated MCP servers; built shared servers for job submission, filesystem access, and cluster interaction, plus the agent harness for sessions, tool routing, and auditable execution
- Serves as the departmental subject-matter expert for AI Agents in Research Information Services; piloted secure adoption across all HPC clusters and leads seminars on AI Agents, MCP, and Skills
- Architected a 20,000-line MLOps Python package for iterative low-code/no-code model training, with Jupyter documentation spanning preprocessing through deployment
- Designed Prometheus/Grafana observability across CPU, GPU, and Slurm job-level metrics, with intelligent alerting connecting anomaly detection to remediation
- Founding member of the team that established the SCCE (GDPR-compliant) and Slurm HPC Model Training clusters; expanded Open OnDemand across 4 environments
- Sole resource for 28 CryoSPARC instances; built an on-the-fly cryo-EM/ET processing pipeline
- Migrated 45 PB of cryo-EM/ET data to dedicated Imaging Storage over 8 months, within the 11 months preceding September 2026
- Transformed module installation system from bare-metal to container-based builds
Highlights
- Manages internship program, reviewing 300-500 applications yearly
- Conducts interviews and coordinates hiring of 15 interns annually
- Mentors interns throughout the summer program
- Established intern-to-full-time pipeline creating career tracks for permanent positions
Highlights
- Built and deployed Open OnDemand instance serving 20,000+ core cluster
- Authored multiple Interactive Applications (Maestro, VMD, Scipion)
- Automated software and module installations across RHEL7/RHEL8
- Organized and taught seminars on HPC programming tools
- Optimized parallel programs (MPI, OpenMP, CUDA) for researchers
Highlights
- Built Prometheus + Grafana metrics collection environment
- Designed cluster monitoring dashboards for resource utilization insights
- Performed routine module installations on RHEL7 HPC Cluster
- Gained proficiency in LSF workload manager administration
Highlights
- Developed VR application using Unity + Meta SDK for pediatric patient training
- Built REST API for AlphaFold-based protein structure prediction
- Compiled deployment documentation for HPC engineering team
Highlights
- CS Head Tutor: hired, trained, managed 9 tutors; built TutoringBot queue system
- CS Tutor: tutored ~20 students in Python, Java, C, data structures, algorithms
- Cloud Application Student Administrator (May 2022 – May 2023): administered a JupyterHub Kubernetes cluster on GCP, including user provisioning, scaling, and OneLogin SSO for secure campus-wide access
Highlights
- Investigated human-robot interaction (HRI) and explainable AI (XAI) in collaboration with the University of North Texas and Oregon State University
- Designed an augmented reality application in Unity and accompanying user tasks to explain how robots navigate using laser scans and camera fields of view
- Conducted a user study investigating privacy in interactions with telepresence and laser-equipped robots
- Contributed to research used to inform lawmakers considering legislation on robots in public spaces
- Served as an investigator on research targeting WeRobot 2021 (Miami) and contributed as an author to a paper targeting the International Conference on Social Robotics 2022
Highlights
- Created Bitcoin trading bot with live price data and technical indicators
- Integrated cryptocurrency exchange APIs for automated trading
- Developed data processing pipelines in Python and Java
Skills & Technologies
Technical expertise
Technologies
Technical expertiseAI infrastructure & automation
MCP (Model Context Protocol)Agent harness designLLM orchestrationSessions & tool routingPipeline executionREST APIsMLOps
HPC & platforms
LSFSlurmOpen OnDemandGPU computingMPIOpenMPCUDAKubernetesApptainer / SingularityGoogle CloudSCCE / GDPR
Observability
PrometheusGrafanaCPU / GPU / job metricsAnomaly detectionIntelligent alerting
Languages & tools
PythonC/C++JavaGoRustBashGitJupyter
Professional development
Red Hat Ansible Automation · self-study
Languages
CommunicationEnglishNative
ArabicNative
FrenchWorking proficiency
SpanishWorking proficiency
Certifications
Professional developmentNVIDIA Certified Associate
AI Infrastructure and Operations
June 2025Focus Areas
Engineering practiceEducation
Learning & discovery
A foundation for what comes next.
Education
Aug 2025
M.S. Computer ScienceGPA 4.0
The University of Texas at Austin — M.S. Computer Science (Expected Dec 2028)
Coursework: Parallel Systems, Deep Learning, Advanced Deep Generative Models, Distributed Systems
May 2023
B.S. Computer ScienceGPA 3.87, Magna Cum Laude
Rhodes College — B.S. Computer Science, Minor: Religious Studies (2019 – 2023)
May 2019
High School DiplomaGPA 3.86
King's Academy, Manja-Madaba, Jordan — High School Diploma
Apr 2016
Scotch College, Perth (Australia)
Round Square Program Global Cultural Exchange — Study Abroad
Selected coursework
Computer scienceUT Austin · Graduate
parallel systemsdeep learningadvanced deep generative modelsdistributed systems
Rhodes College · Undergraduate
parallel systemsdistributed systemsoperating systemsartificial intelligenceautomata theorycomputer organizationprogramming languagesdata structures algorithms
Awards & Honors
Along the way St. Jude Living Our Values 2026 Honoree
Magna Cum Laude
Upsilon Pi Epsilon (CS Honor Society)
Theta Alpha Kappa
Joseph Reeves Hyde Award
Jack U. Russell Award
Presidential Scholar
Dean's List
Student Body President (King's Academy)
President's Award for Outstanding Leadership
Research
Publications & Data Analysis
Publication Record
Peer-reviewed workIEEE/RSJ IROS 2023 • Detroit, MI, USA
Development and Evaluation of Exploratory Experiences to Facilitate Reasoning About Robotic Systems
Abstract
This paper introduces a novel interactive approach — Exploratory Experiences — that aims to improve the ability of people to reason about the capabilities and limitations of robotic technology. We focus on two areas: robot navigation and object detection. We evaluate the Exploratory Experiences with a novel approach that measures the participant's ability to predict when the robot will fail.
Read the paper
Research Keywords
Areas of explorationResearch profile
IEEE XploreProjects
Selected engineering work
Selected projects
Tools built for researchIn production
Pipeline Skill Zoo
Production MCP servers turn research pipelines into tools an AI agent can run on LSF/Slurm. I built and own the platform from proof of concept through daily operation: dedicated pipeline servers, shared job and filesystem tools, and an agent harness for sessions, tool routing, and auditable execution.
Engineering
MLOps Toolkit
20,000-line Python package for iterative, low-code/no-code ML model training. Jupyter documentation guides researchers through preprocessing, training, and deployment.
Engineering
HPC Monitoring
Prometheus and Grafana observability across CPU, GPU, and Slurm job-level metrics, with intelligent alerting that connects anomaly detection to remediation.
Engineering
Open OnDemand
Open OnDemand deployment spanning 4 cluster environments with LSF and Slurm support
Engineering
CryoSPARC Fleet
Operate 28 CryoSPARC instances and an on-the-fly cryo-EM/ET processing pipeline for structural biology research.
Archived
VR Patient Training
Unity + Meta SDK VR application for pediatric radiation oncology patient preparation
Archived
AlphaFold API
REST API endpoint for AlphaFold-based protein structure prediction on HPC
More on GitHub
github.com/walidabualafiaElsewhere
github.com/walidabualafia
Distributed systems, HPC tools, system-level programming, and more
View RepositoriesContact
Start a conversation
Get in touch
Email & elsewhereResume
Experience at a glanceWalid Abu Al-Afia
AI infrastructure & automation · PDF
Location
Based in MemphisMemphis, TN
Open to relocation
Originally from Amman, Jordan