Open to junior Python / AI automation roles

Hello, I'm

Rolly Calma

I build practical automation, AI tools, and developer workflows, backed by 228 PRs opened, 66 merged PRs, and contributions to high-impact repos totaling 1178k+ stars.

228 PRs opened
28 repos contributed
1178k+ contributed-repo stars
Live build loop shipping small verified fixes
Find Patch Verify Follow up

About Me

Self-taught developer from the Philippines. I got into programming because I was tired of doing repetitive things by hand — so I automated them. That became building AI systems, contributing to open-source projects with tens of thousands of stars, and running multi-agent LLM pipelines on local hardware.

I have opened 228 PRs and contributed across 28 repositories, with 66 merged PRs in production codebases. The work spans bug fixes, tests, docs, refactors, and developer tooling across projects like pydantic-ai, chroma, flowsint, langchain, llama_index, mem0, and agno.

I use AI-assisted workflows to build and ship faster — all projects are designed, tested, and maintained by me.

Philippines
Developer & Builder
Self-taught, 42 OSS PRs merged
Python · C# · Docker · Linux
Currently building Multi-agent LLM workspaces, local LLM workflows, and sharper developer utilities for automation-heavy Python projects.
RC
~/about.py

def get_developer():

  return {

    "name": "Rolly Calma",

    "stack": ["Python", "Flask", "Docker"],

    "prs_opened": 228,

    "merged_prs": 66,

    "gpu": "local LLMs ✓",

    "status": "open_to_work",

  }

How I Work

Small fixes, visible progress, clean follow-through

I borrowed this from good design tools: show the work while it is happening. My best PRs are small enough to review quickly, but complete enough to include the bug, the fix, and the verification trail.

01

Find the edge

Look for concrete issues: deprecated APIs, encoding bugs, async loop mistakes, schema mismatches, and missing coverage.

02

Patch narrowly

Change the smallest surface that fixes the behavior, matching the repo style instead of inventing a new pattern.

03

Verify locally

Run focused checks, compile touched modules, and explain why broader tests were or were not needed.

04

Stay with review

Thank maintainers, handle bot process requests, and follow up calmly when CI or review finds something real.

Python Automation

Scripts, pipelines, and bots that run unattended — from file processing workflows to multi-step API integrations.

AI-Powered Tools

Multi-agent systems, local LLM setups, and practical AI tools using Ollama and Claude API — production-ready, not just demos.

Web Apps & APIs

Flask backends, REST APIs, and real-time streaming apps with SSE — from working prototype to deployed and running.

Open Source Contributions

Code merged into projects used by thousands of developers

228 PRs opened across 28 contributed repos, including 66 merged fixes, tests, docs, and refactors. Small, practical changes that make maintained projects easier to use.

Recent pattern Low-risk fixes with verification Deprecation updates, missing edge cases, docs corrections, and targeted tests.
Contributor signal Works inside existing maintainers' style Small PRs, clear repro steps, humble review responses, and local test notes.

Skills & Tools

Languages

Python C# JavaScript HTML/CSS Bash

Tools & Infrastructure

Docker Linux Git FFmpeg Task Scheduler

AI / Data

Ollama Claude API Pandas Local LLMs

Projects

02 / MULTI-AGENT APP Ollama + SSE

Agent Meeting Room

A polished Flask multi-agent workspace where local Ollama agents and optional cloud advisors join by @mention. Recent product upgrades added Code Review, Product Debate, Research, and Planning templates, searchable saved memory, Markdown transcript export, customizable agent personas, free-talk SSE streaming, and a portable Windows .exe release. Built as a practical meeting tool, not just a demo chat app.

Python Flask Ollama Claude API SSE
03 / RAG + EVALS retrieval + guardrails

Mini-RAG

A compact retrieval-augmented generation demo with document loading, semantic search, answer grounding, and lightweight evaluation checks. Built to show the practical pieces employers and clients ask about: chunking, retrieval quality, guardrails, and clear failure notes instead of a black-box chatbot.

Python RAG Evals Guardrails LLM
04 / RELIABILITY UTILS rate + retry

API Utilities (Gist)

Gist

Two battle-tested utilities pulled from production code. A thread-safe token-bucket RateLimiter supporting configurable call budgets per second, plus a @retry decorator with full-jitter exponential backoff — handles hundreds of API requests per session reliably. Zero dependencies, drop-in for any project.

Python Rate Limiting Retry Logic Pure stdlib

Get In Touch

I'm open to junior Python roles, AI automation work, open-source collaboration, and practical tools that need someone persistent enough to ship.