00

Hello, I'm

YAHIA
QANDIL

AI & Data Science
building ML systems, LLM-powered apps,
and end-to-end MLOps pipelines.
SCROLL ↓
01 / About

From notebooks to production.

I'm a final-year AI & Data Science student at ESLSCA University (graduating June 2026), but most of what I'm proud of was learned outside the classroom, by shipping things.

My focus sits at the seam where research-grade ML meets real, deployable systems: training and tuning models is only half the job; the other half is the wiring around them, data versioning, experiment tracking, feature pipelines, model registries, drift monitoring, CI quality gates, and the boring-but-critical infrastructure that lets a model survive contact with production.

Lately I've been going deeper on agentic AI, building RAG pipelines, retrieval-augmented codebase chatbots, and multi-step workflows with LangChain / LangGraph, and on reinforcement learning, where I designed a contextual RL agent for live equity trading. I care about clean abstractions, reproducibility, and writing code my future self won't be ashamed of.

Currently looking for an AI / ML / MLOps role where I can keep learning fast, work alongside engineers who are sharper than me, and contribute to systems that ship.

// At a glance

LocationHeliopolis, Cairo
UniversityESLSCA
MajorAI & Data Science
GraduationJun 2026
LanguagesEN · AR
Status● Open to roles
02 / What I do

Tools & technologies

Python

Primary language for ML, data analysis, and backend services. Comfortable across the scientific stack, NumPy, Pandas, Polars, and idiomatic in async, typing, and packaging conventions.

LLMs & Agentic AI

LangChain, LangGraph, LangSmith, Google Gemini API, FAISS vector search, prompt engineering, RAG pipelines, structure-aware chunking, and n8n workflow automation for agent-to-tool integration.

Reinforcement Learning

Designed a contextual RL agent for live position sizing in the Agentic Trading Bot, with reward shaping on net PnL and safety constraints. Familiar with policy-gradient and value-based methods.

Machine Learning

Built supervised models with scikit-learn and XGBoost; applied feature engineering, cross-validation, hyperparameter tuning, calibration, and rigorous offline evaluation before promoting anything to production.

Deep Learning & NLP

PyTorch, TensorFlow, and Hugging Face Transformers. Evaluated NLP models using BLEU, ROUGE, BERTScore, and perplexity. Comfortable with embeddings, fine-tuning, and tokenizer internals.

MLOps

DVC for data versioning, MLflow for experiment tracking and model registry, FastAPI for model serving, Docker & Docker Compose for packaging, and GitHub Actions for CI/CD with quality gates.

Data & SQL

Strong on Pandas / Polars for transformation and Pandera for schema enforcement. Comfortable in PostgreSQL (Supabase) and the SAP BO Universe semantic layer for governed business data modeling.

BI & Visualization

Power BI for stakeholder-facing interactive dashboards, SAP Web Intelligence for governed reporting, and Matplotlib / Plotly for analysis-time charts that help me actually understand a dataset.

Backend & Cloud

FastAPI for typed Python APIs, Next.js for dashboards, and end-to-end deployment across Render, Vercel, and Supabase Postgres, including third-party API integration (Alpaca Markets, Gemini).

Monitoring & Quality

Evidently for data & model drift, Prometheus for service metrics, Pandera for schema validation, pytest for coverage gates, and flake8 for style, drift and breakage caught at the CI layer, not in production.

Tooling & Collaboration

Git-flow, pull-request review, conventional commits, and team-friendly debugging. Linux-first dev workflow. Comfortable explaining technical work to non-technical stakeholders, picked up at Intercom & Raya.

Soft Skills

Curious by default, low-ego when collaborating, and used to shipping under deadline. Have delivered internal technical sessions on LangChain & presentation skills, comfortable at the whiteboard, not just behind one.

PythonPyTorchTensorFlowHugging FaceLangChainLangGraphLangSmithFAISSGeminiscikit-learnXGBoostPandasPolarsFastAPIDockerMLflowDVCEvidentlyPrometheusGitHub ActionsNext.jsSupabasePostgreSQLPower BIn8n PythonPyTorchTensorFlowHugging FaceLangChainLangGraphLangSmithFAISSGeminiscikit-learnXGBoostPandasPolarsFastAPIDockerMLflowDVCEvidentlyPrometheusGitHub ActionsNext.jsSupabasePostgreSQLPower BIn8n
03 / Career

My career &
experience

Prompt Engineering Intern

AUG 2025 - SEP 2025
Quantum MEA · Prompt Engineering

A focused month inside the prompt-engineering function, where the work felt less like writing prompts and more like designing micro-products. Each prompt template became a contract between an unstructured input and a predictable output, and getting that contract right took the same discipline as writing a unit test. The day-to-day was turning analyst-authored technical documents into clean, structured design docs that downstream engineering teams could act on without a follow-up meeting. The loop was relentless: write, test on real cases, score outputs for completeness and structural fidelity, tighten, repeat. This is where I started to take agentic AI as a craft seriously, not just a topic to read about.

Automation & R&D Intern

JUL 2025 - AUG 2025
Intercom Enterprises · LLM & Agentic AI
  • Designed and built an intelligent codebase chatbot from scratch using LangChain and the Google Gemini API, engineered a structure-aware document splitter that respects function and class boundaries (instead of naïve token chunking) so retrieved context stays semantically coherent.
  • Indexed the splits in a FAISS vector store and tuned the retrieval layer (k, score thresholds, MMR) to balance recall against context-window pressure; the result was sub-second Q&A, folder-level overviews, and an onboarding flow that materially reduced ramp-up time for new developers joining the team.
  • Designed multi-stage prompt-engineering workflows that transform raw analysis documents into structured technical design documents, reducing ambiguity in handoffs between analysts and engineers and cutting back-and-forth in design reviews.
  • Worked hands-on with the full LangChain ecosystem, LangGraph for stateful multi-step agents, LangSmith for tracing and prompt evaluation, and n8n for connecting agents to internal tools and event triggers.
  • Delivered internal technical sessions on LangChain fundamentals, RAG architecture, and presentation skills, packaging what I learned into talks the rest of the team could build on.

Business Intelligence Intern

AUG 2024 - SEP 2024
Intercom Enterprises · Data & Analytics
  • Worked inside SAP Web Intelligence and the BO Universe semantic layer to model business data and build governed, reusable reports for downstream stakeholders.
  • Designed and delivered interactive Power BI dashboards for real client use cases, translating raw transactional data into KPI views, drill-throughs, and slicer-driven exploration that non-technical users could actually navigate.
  • Owned a real-world client data project end-to-end: scoped the question, cleaned and joined the source tables, validated the metrics, and presented the actionable insights directly to internal stakeholders.
  • Picked up the muscle of thinking in business metrics, turning ambiguous asks ("how is this segment performing?") into clean, defensible numbers backed by data lineage.

Software Development Intern

JUL 2024 - AUG 2024
Raya Information Technology · Engineering
  • Embedded with the Software Development team and contributed to live projects across the full development lifecycle, from reading specs and breaking down tickets to writing, testing, and debugging production-grade code.
  • Wrote, reviewed, and shipped code alongside senior engineers, got my first real taste of code review culture, branching strategies, pull-request etiquette, and the difference between code that works and code a team can maintain.
  • Strengthened practical fundamentals in Git workflows, debugging under time pressure, writing unit tests, and collaborating across QA and product roles in a professional team environment.
  • Walked away with a clear preference for systems where quality gates are automated rather than vibes-based, a conviction that later shaped my MLOps work.

B.Sc. in Computing & Digital Technology

OCT 2023 - JUN 2026
ESLSCA University · AI & Data Science Major

Coursework spanning machine learning, deep learning, statistics, data engineering, and software design. Most of my real growth has happened in self-directed projects on top of the curriculum, graduation thesis is the Agentic Trading Bot below.

High School Diploma

2023
SAMA International School · New Cairo, Egypt

General secondary education, graduated 2023.

04 / Selected projects

Projects I've built.

01

Agentic Trading Bot

PythonXGBoostReinforcement LearningFastAPINext.jsSupabase

Graduation project, an autonomous intraday equity trading system built on a Predict-then-Modulate architecture. An XGBoost model provides directional bias from OHLCV features, and a contextual RL agent modulates position sizing, timing, and hold duration based on net PnL feedback per trading block.

A hard safety layer enforces idempotent order placement, partial-fill correction, slippage and fee modeling, and daily state resets. Deployed end-to-end with a Python backend on Render, a Next.js dashboard on Vercel, Supabase Postgres for state, and the Alpaca Markets API for live execution.

02

Adult Income MLOps Pipeline

Pythonscikit-learnXGBoostDVCMLflowFastAPIDocker

End-to-end MLOps pipeline on the UCI Adult Income dataset for binary income classification. Implemented a 3-stage DVC pipeline (prepare, preprocess, train) with all parameters externalized to YAML. Tracked three model experiments in MLflow and registered the best to the Production stage.

Served predictions through a FastAPI app, monitored data drift with Evidently and Prometheus, and enforced quality gates in GitHub Actions CI (flake8, pytest coverage, Pandera schema validation, F1 threshold). Containerized the full stack with Docker Compose.

05 / Contact

Let's build
something.

Open to AI/ML roles where I can grow alongside an experienced team and contribute to meaningful projects. Drop me a line, I read every message.

yahia.qandil183@outlook.com +20 100 914 8956 Heliopolis, Cairo