Skip to content
View Eslam93's full-sized avatar

Block or report Eslam93

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Eslam93/README.md

Eslam Hamed

Technical Lead & AI Solutions Architect — production agentic AI, RAG systems, and cloud-native platforms on .NET and Azure.

📍 Cairo, Egypt · remote  ·  eslamhamed.com  ·  LinkedIn  ·  eslam1311@outlook.com

🟢 Available now for contract work, and open to full-time roles with a start inside a month of agreement.


About me

Technical Lead and AI Solutions Architect with 10+ years in software engineering — backend on C# / .NET since 2016, and 6+ years architecting cloud-native AI platforms on Microsoft Azure.

I've shipped production AI to enterprise customers, including Gulf-region government ministries, formally led a 5-person cross-functional team through a startup's growth phase, and I ship full-stack products solo. Current focus: production agentic AI, RAG at scale, LLMOps, and AI-assisted engineering done with real discipline.

Three things I built, written up as case studies

  • An AI analyst whose every number carries a receipt — executives ask in plain language; the model decides what to ask, a deterministic engine computes, and any claim without a receipt is rejected. Solo build, 2026. The methodology it runs on is open source here: agentic-methodology.
  • Auto-RAG and MerlinX at DXWand — enterprise retrieval in production for 7–10 customers, the agentic SaaS on top of it, and a 73% cut in cost per conversation across 840 agents, proven on a frozen suite before rollout.
  • Career Rafeeq — a paid AI SaaS shipped solo in 14 days, with a statistical eval harness gating every prompt change and 53 integration test files gating every deploy. Live at careerrafeeq.com.

What I do

  • AI / LLM systems — production RAG, agentic frameworks (multi-agent, tool calling, reasoning chains), orchestration with LangGraph / LangChain / LlamaIndex, MCP tool gateways
  • AI operations & safety — LLMOps (prompt/model versioning, monitoring, CI/CD for AI), evaluation harnesses, guardrails, verifiable-evidence architectures, human-in-the-loop review
  • Cloud-native backend — C# / .NET and Python / FastAPI; microservices, event-driven and serverless on Azure (6+ yrs) and AWS; release engineering and repository governance at estate scale
  • Full-stack & solo delivery — strict TypeScript with React / Svelte, end-to-end product ownership
  • Engineering leadership — team management, hiring, mentorship, architecture & code review, engineering standards

Earlier work worth knowing about

  • Egyptian Ministry of Justice — real-time speech-to-text with speaker identification for the court system, selected by the Minister and deployed across several dozen courtrooms
  • Egyptian Cabinet IDSC — semantic legislation search as prime vendor, pre-sale through handoff
  • Cogent — an Arabic-dialect NLP chatbot SaaS that handled 100K+ monthly sessions at 91% intent accuracy (since retired)

Tech I work with

  • AI / LLM — RAG · Agentic systems · LangGraph · LangChain · LlamaIndex · MCP · LLMOps · Weaviate · Azure AI Search
  • Backend — C# · .NET / ASP.NET Core · Python (FastAPI) · Node.js · REST · GraphQL
  • Frontend — TypeScript (strict) · React · Svelte
  • Data — PostgreSQL · SQL Server · MongoDB · Redis · Elasticsearch · Cosmos DB
  • Cloud & DevOps — Azure · AWS · Docker · AKS · Azure DevOps · CI/CD · Kafka · RabbitMQ

Arabic — native · English — full professional proficiency  |  B.Sc. Computer Science, Helwan University  |  Contract now, full-time within a month of agreement

Pinned Loading

  1. Murshid Murshid Public

    Arabic-first RAG over Saudi government-services FAQs — 5-provider bench (Mock/Claude/OpenAI/Gemini live + Falcon-Arabic stub), structured-output judge, red-team adversarial harness, deterministic p…

    Python

  2. A.I.R.A A.I.R.A Public

    Autonomous investment-research backend in .NET 8 — async job pipeline with observable progress, structured reports, and report-grounded chat over SignalR via the OpenAI Responses API.

    C#

  3. agentic-methodology agentic-methodology Public

    A Claude Code harness and a knowledge-base format for building software with an AI assistant: rules, skills, hooks, and evidence-dated facts, derived from real installations.

    Shell

  4. CareerRafiq CareerRafiq Public

    AI job-fit copilot and application tracker — save a job, assess fit against your CVs, decide apply/skip, and keep your search organized.

    TypeScript