Hey there! I’m Youssef Ateya, a Software Engineer who loves building intelligent solutions. My focus is on AI/ML, large-scale data systems, and compiler tech. This site is where I share my projects, essays, and notes. I’m also open for consulting work, so feel free to reach out!
Software Engineer – Digital Wildcatters
June 2024 – July 2025
- Architected and deployed RAG-powered LLM systems for 5 enterprise energy clients, processing 100,000+ technical documents (PDF, Word, Excel, PowerPoint) through distributed Kafka microservices and Python-based ingestion pipelines.
- Engineered end-to-end Azure ML pipelines leveraging Document Intelligence, Computer Vision, and Cognitive Search, achieving 3× faster document retrieval through optimized indexing and caching.
- Developed full-stack features for Collide.io using Ruby on Rails, React, and JavaScript, including real-time chat, caching, and analytics dashboards on Linux environments.
- Containerized AI and backend services using Docker and deployed to Kubernetes, improving scalability and release reliability.
- Fine-tuned transformer models in PyTorch for retrieval and summarization; integrated domain-specific embeddings into RAG workflows.
- Built internal monitoring dashboards using FastAPI and Prometheus for throughput, latency, and document-processing health metrics.
- Wrote automated testing suites in pytest, Jest, and RSpec, achieving 90% coverage with CI/CD automation via Jenkins and GitHub Actions.
Meta – Software Engineering Intern (MLH Fellow, Compiler Systems)
June 2024 – September 2024
- Contributed to Clang/LLVM compiler optimizations for 30% faster compilation in targeted workloads, improving developer performance.
- Collaborated with Meta’s Programming Languages Research team on compiler infrastructure, regression testing, and tooling improvements.
- Authored and published hundreds of pages of LLVM/Clangd documentation adopted by 100+ new contributors, improving onboarding and codebase transparency.
- Implemented cross-platform build/test automation (Linux, macOS, Windows) using CMake and LLVM’s LIT framework.
- Led internal code review sessions and contributed to documentation standards and developer guidelines.
Clang/LLVM Open Source Contributor
September 2024 – Present
- Contributing to Clangd, Clang-Tidy, and ClangIR under the LLVM project, improving diagnostics, static analysis, and IR optimization pipelines.
- Enhanced developer experience for VS Code users by implementing new Clangd Language Server features used by 2M+ developers.
- Authored code analysis checks and refactoring utilities merged into Clang-Tidy.
- Collaborating with LLVM maintainers across subprojects and participating in technical design discussions.
Recommended Reading: Notes/Primer on Clang Compiler Frontend (1) : Introduction and Architecture
A Brief History of Herman Miller
Herman Miller: Ergonomics, Aesthetics, and the Curious Case of Corporate Soul ###(Essay I wrote for a Design class in 2024.)
A visual journey through the history of one of the world’s most influential furniture design companies
If corporations were people—and legally they are—Herman Miller would be that rare specimen: the 100-year-old with impeccable taste who somehow never lost touch with what’s cool. While most companies that reach their hundredth birthday have lost cultural relevance, Herman Miller has maintained a remarkable ability to evolve with changing times while preserving its essential character.…
Read more ⟶
A Tale of Two Worlds
A Tale of Two Worlds Imagining Deterministic and Free-Willed Universes ###(Essay I wrote for a college class in 2022, so take it with a grain of salt.)
I have a confession to make. During a Philosophy class discussion about Determinism and Free Will, I had what I now recognize as a false epiphany: I believed there was no point in debating which system governs our universe. Whether we live in a deterministic or a free-willed world seemed irrelevant.…
Read more ⟶
Co-Intelligent Code: Overcoming Moloch Through Human-AI Collaboration
1. Introduction Artificial intelligence has become the beating heart of modern software engineering, infiltrating every facet of development from the first spark of ideation to the final stages of deployment and beyond. No longer confined to theoretical research, AI now dictates the speed, quality, and efficiency of software. The promise is seductive—automated code generation, seamless bug detection, and predictive analytics that anticipate user needs before they arise. Yet beneath the glossy veneer of innovation lurks a formidable adversary: Moloch.…
Read more ⟶