I build and ship production machine-learning systems — LLM & RAG pipelines, multi-agent frameworks, computer vision and big-data engineering — that turn messy data into decisions.
I'm a Data Scientist and ML Engineer with 4+ years of experience building and deploying machine-learning systems across telecom, fintech, computer vision and NLP. My work spans the full lifecycle — from data ingestion and big-data pipelines to model training, fine-tuning, and getting things running reliably in production.
Lately I work hands-on with LLM pipelines, RAG systems, and multi-agent frameworks (CrewAI) at Etisalat by e&, alongside a solid grounding in classical ML, deep learning, and workflow automation. I hold an MSc in Big Data Analytics Management from Bahçeşehir University.
Four-plus years of compounding tools — picked because they ship, not because they trend.
Six roles, four countries — internships to consultant, EDA to autonomous agents.
"The best models are the ones that quietly run in production and make the next decision easier."
A cross-section of shipped projects — agents, GenAI, vision, speech and forecasting.
Coordinated autonomous agents — navigator, extractor and validator — with CrewAI to scrape catalogues, specs and pricing across e-commerce platforms, feeding clean structured data straight to the BI team.
UiPath bots wired to Python for straight-through processing across contract renewals, ETL and reporting — 95%+ cycle-time reduction.
PEFT/LoRA fine-tuning on open-source LLMs plus a LangChain RAG system over a vector DB for contextual knowledge retrieval.
ARIMA, Prophet and LSTM on multi-year seasonal financial data, producing fiscal-year transaction-volume forecasts for planning teams.
YOLO-based models for real-time object tracking and classification on extracted video keyframes.
Production text-to-speech for English & Urdu with voice cloning via Coqui TTS for enterprise customer engagement.
Multi-language transcription, speaker diarisation and voice-activity detection using Whisper ASR and XLSR.
Transformer-based ABSA pipelines and custom NER for enterprise clients, with client-facing brand-monitoring dashboards.
Collaborative-filtering engine guiding students to career paths from academic profiles — my master's thesis project.
Open to AI/ML engineering and data-science roles, consulting and collaboration. The fastest way to reach me is email.