Hi, I'm Birehan Anteneh.
Building production AI systems
for clients and product teams.
ML / Backend AI Engineer specializing in RAG, LLM agents, and FastAPI platforms. Currently shipping ML systems at The COOL Company. Previously at Adludio. Top-Rated freelancer with 1,000+ hours and $10K+ delivered to 10+ clients.
Top Rated · Upwork
10+ clients shipped
$10K+ delivered
1,000+ hours
Trusted by teams I've built with
01 — Selected work
Real client projects that shipped
Production systems delivered for paying clients — built end-to-end with clean architecture, AI orchestration, and real users on the other side.
FeaturedAI Underwriter — Real Estate Lending Platform
Backend AI Engineer
End-to-end lending platform with AI document validation that replaced spreadsheet-driven loan workflows. Reviewers now handle only flagged exceptions.
Eliminated spreadsheets entirely; reviewers now handle only flagged exceptions.
FeaturedAl-Shalawi — Bilingual AI Legal Platform
Full-Stack AI Developer
A bilingual (Arabic/English) legal SaaS for a Saudi law firm with a RAG document drafter, WhatsApp bot, case management, and Hijri/Gregorian dates.
Drafting cut from hours to minutes. Replaced spreadsheets and WhatsApp groups with one system.
FeaturedSkillBridge — AI-Powered Exam Prep App
AI Software Engineer · Backend
AI-powered exam prep app for high-school students across Africa with curriculum-aligned notes, mock exams, an AI tutor chatbot, and adaptive quizzes — launched on Android and iOS.
1,000+ downloads in first release cycle; reach across 20+ African countries.
FeaturedCreator Cortex — YouTube Title Analyzer & Strategy Platform
Full-Stack Engineer (architecture, backend, frontend, infra)
AI-powered YouTube growth platform: title scoring, RAG-grounded LLM title generation, outlier mining, multi-channel YouTube Analytics OAuth, and a closed feedback loop.
341 endpoints across 118 feature modules; 70k LOC Python backend + 57k LOC React frontend; deployed on Render with Supabase + pgvector.
FeaturedAI Guest Communication for Hotels — Voice + Chat + Messenger
Sole developer (architecture · implementation · deployment · ops)
Omnichannel AI chatbot and voice agent for 4 UK hospitality venues, handling guest inquiries, qualifying event leads, and routing calls 24/7 — across web, Facebook Messenger, and phone.
100% pass rate on a 36-question evaluation suite; live across 4 venues, 24/7 with full lead capture and audit trail.
02 — Experience
Where I've shipped impact
5+ years building production AI / ML systems for ad-tech, lending, healthcare, and education — spanning team-lead, IC engineer, and freelance roles.
Machine Learning Engineer @ The COOL Company
May 2025 — PresentNew York, USA (Remote)
- ›Built a client revenue-forecasting system that predicts daily revenue from scraped domain data, Google PageSpeed metrics, WHOIS info, historical performance, and LLM-generated features — 86%+ accuracy.
- ›Developed a LightGBM floor-price prediction model for an SSP, setting optimal floor prices per ad request and delivering a 7% revenue lift.
PythonLightGBMLLMsFeature EngineeringMachine Learning Engineer @ Adludio
May 2024 — May 2025London, UK (Remote)
- ›Optimized campaign ROI with an automated pacing algorithm using predictive modeling and real-time bid adjustments — 16% KPI improvement.
- ›Built a creative scoring system using historical data and LLMs to evaluate creative variations — 10% lift in engagement, 5% better CTR/CPA.
- ›Created an LLM-driven pipeline that generates on-brand ad concepts aligned with campaign objectives — cut ideation time by 50%.
- ›Built an inventory scoring system using DCN v2 and LTR to optimize bid adjustments — 15% conversion uplift, 10% higher profit margins.
PythonPyTorchDCN v2LTRLLMsAI Software Developer · Team Lead @ Eskalate S.C.
Mar 2023 — Apr 2024Addis Ababa, Ethiopia
- ›Led a team of 18 to launch HakimHub, Ethiopia's first AI-driven medical recommendation platform.
- ›Fine-tuned a Llama 3-based chatbot using AI agents for personalized symptom assessments, integrated with a doctors and hospitals database.
Llama 3AI AgentsPythonNext.jsBackend AI Engineer · AI Agent Developer @ Upwork
Aug 2024 — PresentRemote
- ›Top Rated freelancer — delivered for 10+ clients, 1,000+ hours, $10K+ earned.
- ›Shipped production systems including the AI Underwriter backend for a real-estate lending platform (malamafunding.com).
FastAPINext.jsRAGLLMsGCPSoftware Engineer @ AiQEM Tech
Jul 2023 — Sep 2023Addis Ababa, Ethiopia
- ›Designed and built a React-based dashboard for campaign statistics — engagement rates, trends over time, key advertiser metrics.
ReactJavaScript
03 — Skills
What I work with every day
The tools I reach for first, organized by where they live in the stack. Everything here is something I've shipped to production.
AI / ML Engineering
Backend
Frontend
Cloud · DevOps
Automation · Integrations
04 — Work with me
Three ways I deliver for clients
Engagements I take on most often. Each is scoped to ship something real into production — not a prototype or a slide deck.
AI Backend Engineering
Production FastAPI / Python backends for AI products — from clean architecture to async DB, auth, observability, and cloud deploy.
- FastAPI service with async SQLAlchemy + PostgreSQL
- Auth (JWT / OAuth / OTP), RBAC, encryption
- Cloud Run / Docker deploy + CI/CD
- OpenTelemetry / Sentry / structured logs
RAG · LLM Product Build
End-to-end LLM features: prompt design, RAG pipelines with pgvector, multi-provider routing, structured outputs, and feedback loops.
- pgvector / Pinecone retrieval with proper similarity floors
- Multi-provider LLM gateway (OpenAI / Claude / Gemini / Groq)
- Structured outputs (Pydantic / JSON schema) + retries
- Eval harness + human-in-the-loop pattern
Automation · Agents (n8n, voice, chat)
Self-hosted n8n pipelines, AI voice receptionists, WhatsApp / Messenger bots, and lead-capture flows — wired into your stack.
- n8n workflows (self-hosted Docker stack)
- Vapi + Twilio voice agents
- WhatsApp Cloud API / Messenger bot with signed webhooks
- Quality-gate eval framework with regression tests
05 — Side projects & writing
Open-source experiments and research
Personal projects from my 10 Academy program and ongoing research into LLMs, RAG, and ML pipelines. Most include a Medium write-up and GitHub source.
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.
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.
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.
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.
06 — Achievements & education
Recognition and academic record
Awards & honors
10 Academy Valedictorian — Cohort A
Top of leaderboard in 6-month intensive ML / Generative AI / Data Engineering / Web3 program (less than 4% of applicants completed).
10 Academy — with Distinction
Machine Learning, Generative AI, Data Engineering & Web3 Engineering Training.
2nd Place — A2SV Champions League
$600 prize. Competed against 500+ students; champions-league format with 32 finalists.
View3rd Place — Ethiopian Collegiate Programming Contest (EtCPC)
Out of 80+ teams from universities across Ethiopia.
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, Addis Ababa.
Education
Oct 2019 — Jun 2024
Addis Ababa University
BSc in Software Engineering — AI Stream
OOP, Databases, Software Development, Machine Learning, NLP, Reinforcement Learning.
Dec 2023 — May 2024
10 Academy
Data Science · ML · Generative AI · Web3 (with Distinction, Valedictorian)
Sep 2022 — Sep 2023
A2SV — Africa to Silicon Valley
Software Engineering Program (backed by Google)
Solved 1,000+ algorithm problems (850+ LeetCode, 200+ Codeforces).
07 — About
Engineer first, AI second.
I'm Birehan — an AI/ML engineer with a BSc in Software Engineering (AI Stream) from Addis Ababa University. My foundation comes from A2SV, the Google-backed African software fellowship, where I solved 1,000+ algorithm problems across LeetCode and Codeforces.
I was the valedictorian of 10 Academy Cohort A, completing a 6-month intensive program in machine learning, generative AI, data engineering, and Web3 — top of the leaderboard out of a class where less than 4% of applicants finish.
Today I'm a Machine Learning Engineer at The COOL Company (NY), building revenue-forecasting and floor-price prediction systems for programmatic ad-tech. Previously I shipped predictive systems at Adludio in London. Alongside that, I run an active Top-Rated Upwork practice, building production AI backends and LLM agents for clients across the US, EU, MENA, and Africa.
What drives me: turning AI from a research demo into something a real team uses on Monday morning — with the observability, security, and operational posture to keep it running.
08 — Contact
Have a project? Let's talk.
The fastest way to reach me is email. I reply within a business day.
Open to contract, freelance, and full-time remote roles.