Skip to content
Ali Abbas

Full-stack & AI engineer · Melbourne, Australia

I turn messy information into products people rely on.

I'm Ali Abbas — a full-stack and AI engineer drawn to the whole of a hard problem: the models and retrieval at the core, the data pipelines that feed them, and the product people actually use. I learned it by building and operating Shia Library, a production search platform over a large, multilingual corpus — and I'm building toward AI products that ship at real scale.

View the case studyGitHubResume
220
books ingested
35k+
passages translated
AR · FA · EN
languages
Live
in production

Selected work

Two halves of one platform

A production library — search, and now grounded answers — and the pipeline that feeds it. Built and operated solo.

All work
Flagship · AI / retrieval systems01

Citation-Grounded RAGLive

A question-answering engine that retrieves with a hybrid of BM25 and dense embeddings, answers with Claude using native citations so every sentence links to the exact source span, streams the result, and abstains when the corpus doesn't support an answer — with an eval harness that scores retrieval and faithfulness and gates CI.

Next.js 16TypeScriptClaude (native citations)OpenAI embeddingsBM25 + RRFVercel
266
passages, public-domain
0.91
recall@5 (hybrid)
1.00
faithfulness (Claude, 22-q)
3/3
out-of-corpus abstained
Read case study
AI infrastructure02

LLM GatewayLive

A provider-agnostic LLM gateway whose semantic cache is proven correct — precision, false-positive rate, and a CI gate most managed gateways don't expose.

Next.js 16TypeScriptClaude Haiku (intent judge)OpenAI embeddingsOpenTelemetry gen_ai.*
1.00
cache precision (guarded)
0%
false-positive rate
Case study
Search & retrieval platform03

Shia LibraryLive

Multilingual search over a quarter-million classical passages — now with a grounded "Ask" that answers only from cited sources, or says the sources are silent.

Next.js 15React 19Supabase / pgvectorOpenAI embeddingsClaude (native citations)
~255k
hadith indexed
91%
answers grounded
Case study
Data engineering & LLM orchestration04

Usul PipelineLive

A resilient, cost-optimized ingestion + LLM-translation pipeline that turns scattered source texts into a clean, structured corpus.

Pythonasyncio / httpxClaude (Anthropic)Supabase / PostgresPrompt caching
220
books processed
35k+
passages translated
Case study

Capabilities

What I work on

Grouped by function, not a flat list of keywords.

Languages

  • TypeScript
  • JavaScript
  • Python
  • Java
  • SQL

Frontend

  • React
  • Next.js (App Router)
  • Tailwind / MUI
  • Accessibility
  • Performance

Backend & data

  • Node.js
  • PostgreSQL
  • Supabase
  • pgvector
  • Full-text search
  • Row-level security
  • Caching

AI & retrieval

  • RAG
  • Embeddings
  • Hybrid & semantic search
  • Prompt engineering
  • LLM evaluation
  • Prompt caching
  • Anthropic / OpenAI APIs

Infra & practices

  • Vercel
  • CI/CD (GitHub Actions)
  • Testing (Vitest, Playwright)
  • Git
  • Security headers (nosniff, frame, referrer), secret scanning

Writing

Notes on the hard parts

All writing
24 Jun 2026Coverage is the ceiling: what actually moved my retrieval numbersI tried the famous RAG retrieval upgrades — MMR, RAG-fusion, HyDE, multi-query, a per-source diversity cap. Most did nothing; one made things worse. What actually worked, and why only measurement could tell.7 min18 Apr 2026Making Arabic search actually find thingsWhy a naïve query misses most of its matches in Arabic text, and how diacritic-insensitive search + a client-side mirror fixes it without slowing down.6 min10 Feb 2026A translation pipeline that survives crashesTranslating tens of thousands of passages with an LLM means long, flaky, expensive runs. Here's the checkpointing and quality-gating that makes it safe.5 min

Contact

Let's talk about retrieval, scale, or correctness.

Open to software, AI, and platform engineering internships and graduate roles.

Get in touchali@alimuhammadi.com