https://github.com/codeonthespectrum/codeonthespectrum
https://github.com/codeonthespectrum/codeonthespectrum
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/codeonthespectrum/codeonthespectrum
- Owner: codeonthespectrum
- Created: 2024-12-10T18:02:14.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2026-02-08T10:29:40.000Z (4 months ago)
- Last Synced: 2026-02-08T17:17:12.604Z (4 months ago)
- Size: 38.1 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Welcome! π
Hi! I'm Gabrielly, but you can call me **Kimi** π§©
I'm an **ML Engineer focused on MLOps and AI Infrastructure** with 2 years of experience. I build **production AI systems that scale and cost less**.
---
## π§ Building in Public: Billink AI
I'm currently building **[Billink AI](https://billinkai.com)** β a SaaS platform that automates cloud and AI infrastructure cost auditing using multi-agent LLM pipelines.
**What it does:**
- Analyzes billing data from AWS, OpenAI, and Anthropic
- Identifies waste patterns (idle GPUs, expensive model overuse, storage inefficiencies)
- Generates actionable recommendations with projected savings
**Roadmap:**
- β
Architecture designed (3-stage agent pipeline: Extractor β Analyst β Advisor)
- π§ MVP in development (CSV upload β analysis β PDF report)
- π― Goal: 2 paying customers for validation
**Follow the journey:** I share progress, learnings, and challenges on [LinkedIn](https://br.linkedin.com/in/gabrielly-gomes-ml).
---
π©βπ» **Currently, I am...**
* πΌ **ML Engineer / MLOps Engineer at Cortex:** Architected an Agentic AI system processing **80K+ stores** across **700+ malls** on Kubernetes, enabling a **$2M revenue** product line. Implemented monitoring, alerting, and batch inference pipelines.
* π€ **AI Researcher at UFPI:** Building hybrid BiLSTM-Transformer models for hate speech detection with feedback loop for retraining. [Fine-Tune Baseline](https://github.com/codeonthespectrum/Curupira.ia) | [BiLSTM Baseline](https://github.com/codeonthespectrum/curupira_BILSTM)
---
π οΈ **Tech Stack**
* **MLOps & Infrastructure:** Kubernetes (EKS), Karpenter, Spot Instances, Docker, MLflow, CI/CD for ML, Model Monitoring, Drift Detection
* **Cloud:** AWS (S3, Lambda, EC2, EKS, DynamoDB, Cost Explorer), Terraform, FinOps
* **Machine Learning:** LLMs, Agentic AI, RAG, NLP, TensorFlow, PyTorch, Physics-Informed ML
* **Data Engineering:** PostgreSQL, ClickHouse, Supabase, ETL/Data Pipelines, Analytics Engineering
* **Observability:** Grafana, CloudWatch, HyperDX (P95 Latency, Error Budgeting)
* **Programming:** Python, SQL, PySpark
---
β¨ **Highlights**
* π **Transpetro/Petrobras Hackathon (7th place):** Physics-Informed ML for industrial prediction β identified **$1.89M in fuel savings** and **1,198 tons CO2 avoided**. [Paper](https://dx.doi.org/10.2139/ssrn.6027414) | [Dashboard](https://biofouling-frontend.vercel.app/index.html) | [Model](https://huggingface.co/carpenterbb/biofouling-model) | [REST API](https://carpenterbb-api-transpetro-hackathon.hf.space/)
* π§π· **I Speak KanoΓͺ:** Built the first dataset for **KanoΓͺ** indigenous language preservation. [Documentation](https://github.com/codeonthespectrum/eu-falo-kanoe) | [Dataset](https://huggingface.co/datasets/carpenterbb/i-speak-kanoe)
* π **Social Impact:** Created [Water Inequality Dataset of NE Brazil](https://huggingface.co/datasets/carpenterbb/agua_e_esgoto_nordeste_brasileiro) and published peer-reviewed research. [Paper](https://sol.sbc.org.br/index.php/enucompi/article/view/35664) | [GitHub](https://github.com/codeonthespectrum/freshwater-project)
* π **Cloud Infrastructure Analyst (Freelance):** Audited infrastructure handling **3.26B requests** with **99.92% availability** during Black Friday, analyzing EKS cluster efficiency and Spot Instance resilience.
---
ποΈ **Certifications**
* **Stanford & DeepLearning.ai:** Machine Learning Specialization. [ML Project](https://github.com/codeonthespectrum/predicao_risco_cc)
* **Harvard Aspire Institute:** AI-Integrated Leadership Program (AILP) Alumna
* **DataCamp:** AI Engineer Associate & Data Engineer Associate
---
π **My "Stanford Roadmap"**
- As a neurodivergent learner, I thrive on structure and depth. I am executing a rigorous, self-directed curriculum based on **Stanford University's Computer Science BS** parallel to my formal degree.
π Click to see my full progress & Curriculum
> **Current Phase: Year 1 - Solid Foundation** ποΈ
> Focus: Mathematical rigor and algorithmic thinking.
**Semester 1: Foundation** (From November/25 to May/26)
- [x] **CS106A:** Programming Methodology. [Activities](https://github.com/codeonthespectrum/code-in-place)
- [ ] **Introduction to Mathematical Thinking** (In Progress)
- [ ] **Introduction to Logic** (In Progress)
- [ ] **CS103:** Mathematical Foundations of Computing
- [ ] **CS106B:** Programming Abstractions (In Progress)
**Semester 2: Foundation II** (From June/26 to December/26)
- [ ] **PHYSICS61:** Mechanics
- [ ] **MATH19**: Calculus I
- [ ] **CS107:** Computer Organization & Systems
- [ ] **CS125:** Data & Society
- [ ] **CS109:** Probability for Computer Scientists
- [ ] π§ **Capstone Project 1**
**Year 2: Advanced Core** π
**Semester 3** (From January/27 to June/27)
- [ ] **MATH20:** Calculus II
- [ ] **MATH51:** Linear Algebra & Multivariable Calculus
- [ ] **CS111:** Operating Systems Principles
- [ ] **CS221:** Artificial Intelligence: Principles and Techniques
**Semester 4** (From July/27 to December/27)
- [ ] **CS229:** Machine Learning
- [ ] **CS161**: Design & Analysis of Algorithms
- [ ] **CS205L:** Continuous Mathematical Methods with an Emphasis on Machine Learning
- [ ] π§ **Capstone Project 2**
**Semester 5: Specialization & Quantum** π΅πΌ
**Semester 5** (From January/28 to June/28)
- [ ] **CS22N:** Natural Language Processing with Deep Learning
- [ ] **CS259:** Algorithms Fairness
- [ ] **PHYSICS71:** Quantum
- [ ] π§ **Capstone Project 3**
---
π **Leadership & Volunteering**
* π§βπ« **Teaching Fellow:** Data and AI for Social Analysis course at UFPI
* π§βπ« **AI Instructor:** Teaching AI for women entering tech at NGO
* πΊπ³ **United Nations MGCY:** Major Group for Children and Youth volunteer
---
π¬ **Let's connect**
- πΌ LinkedIn: [Gabrielly Gomes](https://br.linkedin.com/in/gabrielly-gomes-ml)
- π§ Email: [gabrielly.gomes@billinkai.com](mailto:gabrielly.gomes@billinkai.com)