Skip to content
MG

Open to work

Mikiyas Gebrehaweriya

Software Engineer · Backend, Distributed Systems & Applied AI

I build production systems where AI is the operating layer — not a chat box bolted onto the side.

I'm a software engineer in Berlin working on multi-tenant backends, retrieval systems, and AI orchestration. I co-founded PROM — a six-deployable, 274k-line AI-native product operating system — and lead its technical side: the NestJS core API, the Python inference service, the Postgres/pgvector knowledge graph, the billing and entitlement layer, and the customer-facing Next.js app.

See the work ResumeGitHubLinkedIn
By the numbers

Every figure below comes from a real repository, counted rather than estimated.

lines shipped
274k
TypeScript, Python and Prisma across the PROM monorepo
commits authored
602
Of 605 on PROM, between May and August 2026
REST endpoints
337
Across 37 NestJS modules in one modular monolith
database models
69
62 forward migrations, zero destructive rollbacks
  • TypeScript
  • NestJS
  • Python
  • FastAPI
  • PostgreSQL
  • Prisma
  • pgvector
  • Redis
  • BullMQ
  • Docker
  • Turborepo
  • Next.js
  • React
  • Tailwind
  • Socket.IO
  • Stripe
  • OpenTelemetry
  • Anthropic
  • MCP
  • OpenAPI
  • Zod
  • Jest
  • pytest
  • MinIO
Selected work

Systems I designed and shipped

Not screenshots and stack lists. Each one is a case study covering the problem, the architecture, the decisions I would defend, and the things that went wrong.

All 4 projects
ProductMay 2026 — Present
Active

PROM

An AI-native operating system for product development

Six deployables, 274,000 lines, a company of two. PROM takes a team from raw idea to shipped product inside a single workflow engine, where every artefact — personas, decisions, specs, tasks, launches — lands in a knowledge graph the AI reasons over. I co-founded it and own the technical side: the NestJS core API, the Python inference service, the Postgres/pgvector graph, billing and entitlements, the customer web app, an internal staff console, and a CLI that puts the whole thing inside your editor over MCP.

274k

lines of code

6

deployables

337

REST endpoints

69

Prisma models

NestJSPythonpgvectorMulti-tenantLLM tooling
Read the case study
Competition2024
Prototype

Porsche Customer Relations Hub

Winning entry — Porsche Digital Campus Challenge

An AI-powered customer relations platform for Porsche: a multi-modal assistant that resolves owner issues in the My Porsche app using semantic retrieval over Porsche's own knowledge sources, paired with an agent console that gives human CR staff the full session context the moment a case escalates. Our team took first place in the Customer Relations track.

AI agentRAGMulti-modalAWS
Read the case study
Platform2024 — 2025
Prototype

SociaLink

A unified operational data store for social presence

SociaLink pulls a person's activity across social platforms into one operational data store and makes it answerable in plain language. Built as a polyglot-persistence exercise that turned into a real system: layered ingestion pipelines, hybrid full-text and vector retrieval, and an assistant with awareness of the whole store rather than a single document.

DjangoPolyglot persistenceHybrid searchDocker
Read the case study
From the blog

What I build, and what it teaches me

Decisions I had to reason my way into, bugs that cost me an afternoon, and the occasional thing I got wrong. Written mostly so that I remember.

Read the blog
Capabilities

What I actually do

Five areas, each with evidence attached. The full matrix rates every tool and says what I built with it.

Full skill matrix

Backend & API

Where most of my work lives: modular monoliths, guard chains, background workers, and contracts that hold under load.

TypeScript · NestJS · Node.js · Python

Data & Persistence

Schema-first. I would rather spend a day on a migration than a quarter on a data-fix script.

PostgreSQL · Prisma · Data modelling

Applied AI & Retrieval

Treating models as an unreliable dependency you engineer around, not a magic box you trust.

RAG architecture · Embeddings & vector search · LLM tool calling · Anthropic Claude API

Frontend & Product

Enough depth to own a product surface end to end, including the parts that are actually hard: state, realtime and accessibility.

React 19 · Next.js App Router · Tailwind CSS

Platform, Security & Ops

The unglamorous half. Most of what makes software trustworthy happens here.

Docker & Compose · Turborepo · Multi-tenancy · AuthN / AuthZ

Availability

Internship · Working student · Junior backend / platform / AI engineering

Berlin-based, open to hybrid or remote across the EU. If you are building something where the backend is the hard part — tenancy, retrieval, cost control, or an AI layer that has to be trustworthy — I would like to hear about it.

Get in touch Read my resume