ryneandal

Joined 12 years ago

Karma
738
Submissions
264
Member since
Nov 25
33 year old software dev located in sioux falls sd, usa. .net/x++, php, bash, python.

[ my public key: https://keybase.io/ryne; my proof: https://keybase.io/ryne/sigs/xNPAdailtZCiNxXSmgIfCwlcbbJNKL3ZjS5dSFMGEkU ]

View on Hacker News

Recent submissions

Comment · 1 month ago
Comment · 1 month ago
Location: Valencia, Spain

Remote: Yes

Willing to relocate: No

Technologies: Python (FastAPI, Langchain, LangGraph, Django), PHP (Laravel, Drupal)

Résumé/CV: https://ryneandal.github.io/ryne-andal-dnv-resume.pdf

15+ years in backend systems, architecture, legacy modernization, and infrastructure. Recent AI work includes production RAG/codebase retrieval, MCP services with approval controls, enterprise document retrieval, and building custom AI benchmark/eval.

Python (Django, FastAPI, Flask), PHP (Laravel, Drupal), PostgreSQL, APIs, Docker, Kubernetes, CI/CD, Linux, RAG, LangChain/LangGraph, MCP, vector databases, and AI agents/ agent evaluation.

Comment · 4 months ago
Comment · 4 months ago
Comment · 5 months ago
Comment · 5 months ago
Comment · 5 months ago
Comment · 6 months ago
Comment · 7 months ago
Comment · 8 months ago
Comment · 9 months ago
Location: Valencia, Spain (CET) Remote: Yes (US & EU; daily 4-hour overlap with US business hours) Willing to relocate: No Technologies: Python (Django, Pydantic/FastAPI, LangChain, LangGraph), PHP (Laravel, Drupal), Docker Résumé/CV: https://linkedin.com/in/ryneandal (full CV available on request) Email: [email protected]

Currently have part-time/fractional availability for independent consulting/contract work. Recent work has involved AI integrations (LangChain, LangGraph, FastMCP), data pipelines, CI/CD workflow automations, etc. 15+ years of experience in software development.

Comment · 1 year ago
I haven't done exhaustive testing of all top-performing models on the HF Embedding Leaderboard (https://huggingface.co/spaces/mteb/leaderboard) but I have tested a number of them extensively in the past month or two. The two best API provider models I've tested are:

- JinaAI (https://jina.ai/embeddings/) v3 and v4 performed well in my testing. - Google's Gemini-001 model (https://ai.google.dev/gemini-api/docs/models#gemini-embeddin...).

Overall, both were surpassed by Qwen3-8b (https://huggingface.co/Qwen/Qwen3-Embedding-8B).

Note, this was specifically regarding English and Code embedding generation/retrieval, with reranking.

Comment · 2 years ago
IMO the PyTorch getting started tutorials are really good (https://pytorch.org/tutorials/beginner/basics/intro.html).

A classifier for handwritten digits in the MNIST dataset is generally considered the "Hello World" of neural networks. I went over it in a course, but there are countless tutorials to be found online, i.e. https://www.digitalocean.com/community/tutorials/introductio...

Once you begin to understand how to handle data and how to define layers, you can start playing around with whatever your heart desires. The rabbit hole is vast and endless :)

Comment · 2 years ago
Mine was $750 :(

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton