Currently · SDE II at Niyyah

Mobile EngineerAI Engineer

Omar Salama

React Native & Python. RAG pipelines, on-device LLMs, five years of shipped products.

5 yrs shipping mobileProduction RAG & agentic systemsOn-device LLM fine-tuning

Open to remote (CET/EU) & relocation · Giza, Egypt

Get in touchDownload CVLinkedInGitHub
About

Two tracks, one engineer

Software engineer, five years in. Two tracks that keep overlapping — AI systems and mobile.

Production LLM systems end to end: retrieval and RAG with hybrid search and cross-encoder reranking, agentic orchestration that splits routing from generation, fine-tuning with SFT and DPO, and the evaluation tooling that keeps all of it honest. On the mobile side, native Android and iOS led to React Native for years of shipped cross-platform features — and most recently a fine-tuned LLM running fully on-device in a React Native app.

3.5 years at Keepoala, a year-plus LLM-training contract at Turing, now SDE II at Niyyah across the AI backend and React Native app. On the side, OpenSpace — an on-device therapy companion running a Gemma-4 E2B model fine-tuned and published as TheraSpace on HuggingFace.

The work I like best runs the whole length of a feature: the model, the retrieval that feeds it, and the app it ships in.

Experience

Where I've worked

Sep 2025 - Present

Niyyah

SDE II

Work spans the AI backend and the React Native app of a production Islamic companion app — ~128 merged PRs in six months.

  • Build the retrieval-grounded answer pipeline: a router gathers and ranks sources, a separate model generates a cited, streamed answer, with multi-provider model routing and fallback for quality, cost, and reliability.
  • Built the evaluation tooling from scratch — LLM-as-judge scoring, retrieval-quality metrics, regression checks with alerting — 625 tests across 52 suites in the AI core.
  • Cut input tokens per answer 10–20% and made responses resilient: a server-side streaming proxy persists in-flight answers so they survive the app closing or losing connection, plus conversation summarization keeps long chats within budget.
  • Plan features end to end — a personalized 30-day guided journey, a conversational onboarding flow — then ship the React Native side.
PythonFastAPIReact NativeTypeScriptLLM evals

Jun 2024 - Sep 2025

Turing

Python Developer (LLM Training)

LLM-training contractor; SFT for domain-specific applications.

  • Promoted to pod lead, guiding a 4-person pod and reporting on performance.
  • Built internal Jupyter tooling for cross-pod progress reporting.
PythonSFTJupyter

May 2021 - Oct 2024

Keepoala

Software Developer

Core mobile engineer on a two-person mobile team, from working student onward.

  • Built and shipped the React Native consumer app (iOS + Android) over 3.5 years, including a full UI/UX redesign pass and reusable design-system components.
  • Backend integrations on Firebase Cloud Functions — BillBee, WeClapp, Algolia, and a Shopify merchant plugin.
  • Partner-shop analytics dashboard (React + R-Shiny): retention curves, NPS, and order metrics.
React NativeTypeScriptFirebaseR-Shiny

Oct 2021 - Mar 2022; Jan 2025 - Apr 2025

Karat

Interview Engineer

Two contract stints as a technical interviewer.

  • Interviewed software-engineering candidates on behalf of Karat's enterprise clients using calibrated rubrics — structured coding and problem-solving screens.

2017 - 2022

B.Sc. Computer Engineering · Cairo University

Very Good with honors · Graduation project: NeuroGames (graded Excellent)

Projects

Things I've built

Skills

What I work with

Solid = daily drivers

Mobile

React NativeTypeScriptllama.rniOS (Swift)Android (Kotlin, Java)MMKVKeychainReact Navigationdeep linking

LLMs / Fine-tuning

SFTDPOLoRAGGUF quantizationQLoRAllama.cppprompt caching

RAG / Retrieval

hybrid searchcross-encoder rerankingbge-m3BM25RRFChromaDB

Agents

tool-calling orchestrationcost-aware model routingtool budgetsguardrailsstructured-output routing

Evaluation & observability

LLM-judge pipelinesRAGTriad (precision/faithfulness/relevance)hallucination guardspairwise bake-offshealth checksalerting

Backend & Infra

PythonFastAPIModalNode.jsExpressFirebase Cloud FunctionsAWS (Lambda, EC2)HuggingFaceLangChain

AI-assisted dev

Claude CodeCursorcustom skillssubagentsslash commands

Languages

TypeScriptPythonJavaScriptSwiftKotlinJavaCC++
Contact

Let's talk.

Looking for mobile or AI engineering roles — remote (CET/EU) or with relocation. Email me and I’ll usually reply the same day.

osalama710@gmail.com
LinkedInGitHubDownload CV