Moustafa Zein

Rising Codementor

US$15.00

For every 15 mins

ABOUT ME

Senior Software Engineer - Java

AI & Data Engineering Manager with 12 years of technical expertise and 6+ years of leadership.
Expert in building production LLM systems, multi-agent orchestration, and scalable data infrastructure. Currently architecting LLM systems at Finiti Legal and leading ML infrastructure at Haat Delivery.

CORE STRENGTHS:

Leadership: Built teams of 0→14 engineers (MaxAB), managed 15-engineer teams (Microsoft). Establish engineering standards, mentor talent, and deliver technical roadmaps.
LLM & Agentic AI: Multi-agent orchestration (Pydantic AI, LangGraph, MCP), fine-tuning, inference optimization (<100ms latency), RAG systems, domain-specific LLM training, benchmarking, evaluation frameworks (98% accuracy).
Scalable Systems: Architected pipelines handling 120M+ daily records, served 150K concurrent users, processed 2M transactions/second: Real-time ETL (Kafka, Flink), data warehousing (Synapse, clickhouse, BigQuery).
Product Impact: $85M in funding achievements, 900M EGP in revenue, 4.5x DAU growth (40K→180K), 100% increase in orders (9.8K→18K daily). Delivered features solving real customer problems.
Technical Expertise: Java, Python, Spring Boot, FastAPI, Django, microservices, event sourcing. Azure, AWS, and GCP cloud platforms.
Research Background: 10+ peer-reviewed publications in machine learning and optimization. Advisor: Prof. Aboul Ella Hassanien, Prof. Amr Badr.

TRACK RECORD:

Finiti Legal: Built a multi-agent LLM system; lawyers 2x more productive
Haat Delivery: ML infrastructure handling 120M records/day; 100% order growth
Microsoft: LLM article generation; 4.5x DAU growth; led 15-engineer team
MaxAB: Shipped fintech from scratch; $85M funding contribution; 14-engineer team
Autonomic [Ford company]: Real-time ML systems; -75% production issues
elmenus: Fleet operations + ML; 50% faster delivery

AGENTIC AI EXPERTISE:

Multi-agent orchestration (LangGraph, Pydantic AI, MCP)
Agentic RAG architectures (tool use, planning, reflection)
LLM inference optimization (prompt caching, structured outputs, model routing)
RLHF/fine-tuning pipelines for domain adaptation
Vision-language models (Gemini Flash, GPT-4V)
Production LLM evaluation & monitoring (Logfire)

Cairo (+03:00)

Joined May 2021

EXPERTISE

Python

7 years experience

LLM

3 years experience

7 years experience

10 years experience

7 years experience

6 years experience

7 years experience

REVIEWS FROM CLIENTS

Moustafa's profile has been carefully vetted and approved as a Codementor. Connect with Moustafa now, and leave a review for them once you're done!

SOCIAL PRESENCE

GitHub

A-Deep-Regression-Model-in-Keras

A Deep Regression Model in Keras

Jupyter Notebook

LeetCode

Leet Code Problem Solving

Java

EMPLOYMENTS

Lead AI Engineer

RemoFirst

2026-05-01-Present

I am leading the RemoHire team that is building an AI-native hiring platform that replaces the traditional, slow, and biased screening...

I am leading the RemoHire team that is building an AI-native hiring platform that replaces the traditional, slow, and biased screening process with intelligent AI conversations. Instead of recruiters spending hours on repetitive phone screens and manual resume matching, RemoHire puts AI at the center of the hiring workflow.

Python

PostgreSQL

Docker

Python

PostgreSQL

Docker

NLP

Kubernetes

Next.js

Fastapi

Conversational AI

AWS

Voice AI

LLM

Langgraph

Llm agents

Ml evaluation techniques

Llm building Deployment

Hands-on Engineering Lead (AI, Data, MLOps, Data engineering)

Haat delivery

2024-10-01-2026-05-01

Hired and established the ML algorithms and data infrastructure team, and developed AI/data infrastructure using Azure cloud solu...

Hired and established the ML algorithms and data infrastructure team, and developed AI/data infrastructure using Azure cloud solutions. 
Developed ML and LLM models to enhance user experience, particularly by reducing delivery estimated time by 20 minutes and personalizing dish recommendations. 
Built robust data streaming and warehouse pipelines to handle 120M records daily and store 4.5TB of data over the last six months.
Implemented an automated vehicle routing system to cover 24 areas, resulting in a 100% increase in daily orders from 9.8K to 18K within 8 months.
Delivered both the business and technical roadmaps for ML usage and data engineering in food delivery, contributing to securing the next funding round.

Python

PostgreSQL

Google BigQuery

Python

PostgreSQL

Google BigQuery

Docker

Team collaboration

Strategy

Infrastructure

Project planning

Kubernetes

Grafana

MQTT

Data Engineering

PyTorch

Helm

ClickHouse

MLOps

Langchain

LLM

RAG

Llm inference stacks

Llm inference tuning

Timeseries databases

AI/AI/ML Tech Lead

Finiti Legal

2025-09-01-2026-03-01

TEAM LEADERSHIP

Lead engineering team on LLM systems; set standards for prompt engineering, fine-tuning, and model evaluati...

TEAM LEADERSHIP

Lead engineering team on LLM systems; set standards for prompt engineering, fine-tuning, and model evaluation
Review designs/PRs; unblock execution
Partner with domain experts (lawyers) to translate legal requirements

MULTI-AGENT ORCHESTRATION

Designed serial/parallel workflows using Pydantic AI, LangGraph, and MCP
4-agent system: contract parsing → risk analysis → compliance checking → recommendations
Lawyers review contracts 10x faster (20 hrs → 2 hr)

INFERENCE OPTIMIZATION

Optimized Azure OpenAI inference: <100ms latency (was 30-45s)
Prompt caching: -65% token usage, -$2K/month cost
Constrained JSON outputs: 73% token reduction

LLM FINE-TUNING & EVALUATION

Built an evaluation framework comparing LLM outputs vs human lawyer benchmarks
Achieved 98% accuracy on contract risk identification
Implemented the RLHF pipeline with lawyer feedback for domain-specific accuracy
Integrated Pinecone RAG: legal precedent retrieval (95%+ accuracy)

LEGAL PRODUCTS SHIPPED

Document Drafting: LLM generates contracts from templates; 2x lawyer productivity
Contract Review: Multi-agent system flags risks, missing clauses, compliance gaps
Precedent Search: RAG-powered retrieval of relevant case law and regulations
Impact: Enabled legal professionals to 2x daily document throughput

TECHNICAL DECISIONS

Choose Pydantic AI for type-safe structured outputs (critical for legal accuracy)
LangGraph for state management (legal reasoning requires a multi-step context)
Azure OpenAI for enterprise compliance and data residency requirements

Python

PostgreSQL

Azure

Python

PostgreSQL

Azure

Docker

Infrastructure

Kubernetes

Terraform

Next.js

PyTorch

OpenAI

Fastapi

Azure synapse

LLM

Google gemini

Pinecone

Langgraph

Ai model optimization

Anthropic

Llm inference stacks

PROJECTS

Arrow 3 based on OpenText

2017

Purpose and Description: The purpose of this project is providing a correspondence and document management system based on OpenText as a...

Purpose and Description: The purpose of this project is providing a correspondence and document management system based on OpenText as a third party; Moreover, applying new requirements that are related to the ministry of Environment in Saudi Arabia. My Role and Achievements: 1. Implementing the main functions of Arrow based on OpenText. 2. Analyzing and documenting the new requirements of the ministry of Environment. 3. Designing and implementing new features in Arrow. 4. Participating in changing the front-end of Arrow based on new technologies such as Angular 2.

Arrow 2 based on Cloud Domains

2016

Purpose and Description: This project included some important stages in developing Arrow Product such as applying the concept of cloud, p...

Purpose and Description: This project included some important stages in developing Arrow Product such as applying the concept of cloud, performance optimization, customize some features, fixing postponed and critical issues, and documenting the main functions of arrow. My Role and Achievements: 1. Applying cloud concepts in several modules with some technologies such as ESB. 2. Recovering and fixing bugs in Data access layer (Hibernate layer). 3. Working with the team on enhancing the product performance. 4. Customizing some features in the project such sending Mail and SMS. 5. Introducing and applying the idea of technical documentation for the project.