LLM applications
Agentic workflows, MCP integrations, RAG systems, evaluation, and the product interfaces around them.
Explore my work, skills, and experience using information from this site.
Deployed employer work, client delivery, and portfolio projects in AI and data engineering.
An internal AI workflow that turns documents, links, or plain text into structured records, asks for missing information, and executes an approved action after human review.
A client reporting pipeline built over more than 1TB of source data and 7.2M reporting rows, using dbt, Amazon QuickSight, and scheduled daily refreshes.
An internal tool that generates a résumé and cover letter for a selected job, then uses LLM-based evaluation to score relevance and consistency.
A portfolio project exploring retrieval and generation for contract questions, with RAGAS used to evaluate the pipeline.
A fully dockerized data-warehouse stack for traffic-trajectory data from swarm drones (pNEUMA): Airflow ingests large CSVs (~87MB each), and dbt builds tested, documented staging/production models for spatial-temporal analysis.
A training project that uses RAG and open-source LLMs to generate Amharic text ads for Telegram channels.
A training project that converts natural-language questions into SQL and returns the result through Redash.

I'm an AI engineer in Addis Ababa. I build agentic applications with LLMs, MCP, and RAG, along with the data systems and interfaces they need to be useful.
My recent work includes internal AI workflows, résumé and cover-letter generation used by trainees, and an automated reporting pipeline for a client. I also teach AI, data engineering, data science, and machine learning at 10 Academy.
I start with the problem and available data, build a small working version, test it with real examples, and improve it from there.
Tools I have used across AI applications, software, data pipelines, and machine learning.
Agentic workflows, MCP integrations, RAG systems, evaluation, and the product interfaces around them.
Data pipelines, dbt models, Airflow workflows, reporting layers, and automated dashboards.
Practical machine-learning and NLP work, from preparing the data to evaluating the result.
Exploratory analysis, clear reporting, and decision-focused views of complex datasets.
Choose what to emphasize. The CV switches its summary, skills, and selected projects, then lets you print or save the result as a PDF.
Choose a CV focus →