01: Selected work
Production systems that shipped
Client and product work from architecture through deploy: backends, LLM features, and the ops glue that keeps them running for real users.
02: Experience
Where I've shipped impact
Production ML and full-stack delivery in programmatic ad-tech, team-led health AI, and advertiser tooling, spanning modeling, LLM pipelines, and React dashboards.
Machine Learning Engineer @ The COOL Company
May 2025 to Jan 2026New York, USA (Remote)
- ›Built a data-driven AI floor-price prediction system using LightGBM to dynamically optimize pricing per ad request for DSPs, resulting in a 7% increase in revenue.
- ›Built a client revenue-forecasting system that predicts daily revenue using scraped domain data, Google PageSpeed metrics, WHOIS information, historical performance data, and LLM-generated features, achieving 86%+ prediction accuracy.
PythonLightGBMLLMsAI IntegrationFeature EngineeringDSP / Programmatic AdsWeb Scraping & SignalsModel DeploymentMachine Learning Engineer @ Adludio
May 2024 to May 2025London, UK (Remote)
- ›Improved campaign ROI with an automated pacing algorithm (predictive modeling + real-time bid adjustments), with ~16% KPI lift.
- ›Shipped a creative scoring system (history + LLMs) to rank creative variants, with ~10% engagement lift and ~5% CTR/CPA improvement.
- ›Shipped an LLM pipeline for on-brand ad concepts aligned to campaign goals and cut creative ideation time by about half.
- ›Shipped inventory scoring (DCN v2 + LTR) to tune bids across publishers, formats, and devices, with ~15% conversion lift and ~10% margin lift.
PythonPyTorchDCN v2LTRLLMsAI Software Developer · Team Lead @ Eskalate S.C.
Mar 2023 to Apr 2024Remote
- ›Led a cross-functional team to launch HakimHub, a first-of-its-kind AI-powered medical recommendation platform, using Jira for structured planning, task tracking, and coordination through delivery.
- ›Fine-tuned a Llama 3-based chatbot using AI agents for personalized symptom assessments and follow-ups, integrated with tooling to query doctors and hospitals.
Llama 3AI AgentsPythonNext.jsSoftware Engineer @ AiQEM Tech
Jul 2023 to Sep 2023Remote
- ›Built a React dashboard for advertisers to visualize campaign performance, including engagement, trends, and key metrics over time.
- ›Partnered with product and stakeholders to gather requirements and tighten dashboard usability.
ReactJavaScriptDashboards
03: Skills
What I work with every day
The tools I reach for first, organized by where they live in the stack. Primary stack is highlighted; everything here has shipped to production.
AI / ML Engineering
PrimaryBackend
PrimaryCloud · DevOps
PrimaryFrontend
Automation · Integrations
04: Side projects & research
ML experiments and open-source research
Where I explore LLM fine-tuning, RAG architectures, and ML pipelines. Most include a Medium write-up and GitHub source.
Legal Contract Advisor — High-Precision RAG for Legal Q&A
Feb 2024
Contract Q&A RAG system for Lizzy AI built to deliver high-precision answers on legal documents using semantic chunking, hybrid retrieval, and a fully evaluated RAG pipeline.
Redash Chatbot Add-on — Agentic RAG for Data Analysis
2024
Conversational chatbot add-on for Redash that translates natural-language questions into SQL/queries against existing dashboards using an agentic RAG approach.
Loan Risk Prediction ML Pipeline (LightGBM + FLAML + MLflow)
Sep 2024
End-to-end loan risk prediction pipeline: data ingestion, preprocessing, LightGBM training, FLAML hyperparameter tuning, MLflow tracking, Docker, and CI/CD retraining via GitHub Actions.
Fine-tuning Llama 2 for Amharic Text Generation
2024
Fine-tuned Llama 2 to enable quality embeddings and text generation in Amharic, then used it inside a RAG-based ad-copy builder for the Ethiopian market.
Automated Storyboard Synthesis for Digital Advertising
Feb 2024
ML solution that automated storyboard creation for digital ads — combining EDA on creative assets, YOLO object detection, and image generation.
n8n Content Pipeline — Topic to Published SEO Article in Under 4 Minutes
2025
Self-hosted n8n pipeline triggered by one Telegram command. Six stages: parallel research, SEO analysis, multi-agent Writer→Critic→Refiner loop, Claude QA, final scoring.
05: Achievements & education
Recognition and academic record
Awards & honors
10 Academy Cohort A, Valedictorian (with Distinction)
Top of leaderboard in a 6-month intensive Machine Learning, Generative AI, Data Engineering, and Web3 program. Less than 4% of applicants completed.
2nd Place, A2SV Champions League
Competed against 500+ students; champions-league format with 32 finalists.
View3rd Place, Collegiate Programming Contest (EtCPC)
Out of 80+ teams from universities across the region.
ViewTop Problem Solver, A2SV G4 Camp II
Solved every camp coding challenge; 1st place top problem-solver certificate.
Winner, DevFest 2022 Hackathon
Hosted by Google Developers Group.
Education
Oct 2019 to Jun 2024
AAU
BSc in Software Engineering (AI Stream)
OOP, Databases, Software Development, Machine Learning, NLP, Reinforcement Learning.
Dec 2023 to May 2024
10 Academy
Data Science · ML · Generative AI · Web3 (Distinction, Valedictorian)
Sep 2022 to Sep 2023
A2SV (Africa to Silicon Valley)
Software Engineering Program (backed by Google)
Solved 1,000+ algorithm problems (850+ LeetCode, 200+ Codeforces).
06: About
Engineer first, AI second.
I'm Birehan, an AI software engineer. I build production systems where AI is wired into the product: services and APIs, data pipelines, and LLM-backed features people use every week. At The COOL Company in New York that was intelligent pricing and revenue tooling inside programmatic ads. At Adludio in London before that it was pacing and creative workflows, plus an LLM-assisted pipeline that cut concept iteration time about in half. The through-line is software that stays reliable when intelligence sits in the critical path.
I lead with engineering discipline, then sweat the AI details: contracts, evaluation, rollout, and the boring glue so teams trust what ships. That sits on a Software Engineering degree with an AI stream, 1,000+ competitive problems through A2SV, and valedictorian at 10 Academy Cohort A. Same bar everywhere: ship AI software that still makes sense after launch, not only in a demo.
07: Contact
Hiring or have a project? Let's talk.
Email or WhatsApp both work. I aim to reply within a business day on email; WhatsApp is fine for a quick ping or time-sensitive threads.
Open to full-time remote and contract AI / ML engineering roles./in/birehan
@birehan
Medium (@birehan)
+251982070195
Email to schedule