Skip to content
View negash's full-sized avatar
4 followers · 7 following

Achievements

Achievement: Pull Sharkx2

Achievements

Achievement: Pull Sharkx2

Block or report negash

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.

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
negash/README.md

Banner

Hi there

I’m a Developer Leader, AI Engineer, and LLM Application Developer & Tester.

10+ years of experience building full-stack, zero-to-one products and enterprise platforms across both startup and regulated environments. I’m a strong generalist with a hacker mentality—high agency, a bias toward shipping, and comfort navigating ambiguity, technical debt, and shifting priorities.

My current focus is on applied AI systems, including LLM-powered products, autonomous agents, and RAG pipelines. I enjoy taking ideas from early experimentation all the way through to production-ready systems.

Pinned Loading

  1. V2_Bank_recommendation V2_Bank_recommendation Public

    RAG Based An AI-powered Banking recommendation system. It combines semantic search with large language models to generate data-grounded financial recommendations.

    Python 1

  2. V2_Flight_Comparison V2_Flight_Comparison Public

    A deterministic, production-ready flight comparison API built with FastAPI , LangChain structured output , OpenAI , and Amadeus Flight Search , with Opik observability for tracing and evaluation .

    Python 1

  3. AI_10_Best_Practices AI_10_Best_Practices Public

    A practical guide to building cost-efficient AI systems. Covers prompt design, caching, batching, and model selection to reduce token usage, lower costs, and improve performance.

  4. LLMs-from-scratch LLMs-from-scratch Public

    Forked from rasbt/LLMs-from-scratch

    Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

    Jupyter Notebook

  5. mcp-use mcp-use Public

    Forked from mcp-use/mcp-use

    mcp-use is the easiest way to interact with mcp servers with custom agents

    Python

  6. earthdata-mcp earthdata-mcp Public

    Forked from nasa/earthdata-mcp

    Python