Skip to content
View Rodrigo-Palma's full-sized avatar

Block or report Rodrigo-Palma

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
Rodrigo-Palma/README.md

Hi, I'm Rodrigo Palma πŸ‘‹

Senior Data & AI Engineer β€” I take systems from raw data to ML/LLM in production:
pipelines, RAG, agents, evals, and the boring reliable plumbing included.
🌎 Porto Alegre, Brazil Β· 🟒 Open to remote Data & AI roles (worldwide) Β· πŸ“© email.rodrigopalma@gmail.com

LinkedIn


πŸ’₯ Impact, not just code

  • πŸ›οΈ Modernized the data stack of a public institution managing a R$100M+ budget β€” resilience and reliability for systems thousands of people depend on.
  • πŸ’° Cut ~R$200k/year in operating costs with reproducible ELT pipelines.
  • πŸ“Š Built AI + NLP analytics products informing decisions for 2,000+ staff at an institution that delivered 2.65M+ legal-aid services in 2025.
  • πŸ›‘οΈ Shipped LLMs / RAG to production with guardrails and offline evals β€” not demos.
  • πŸ† Co-designed an award-winning analytics product that fairly benchmarks workload across units of a public institution β€” 2nd place at a national public-sector innovation congress (2026).

πŸ’‘ Public portfolio started Jun/2026. 8+ years building data/ML systems in production; the institutional systems above are internal (public sector, under NDA) and can't be open-sourced β€” these repos are where I build in the open.

πŸ“Œ Featured projects

Project What it is Domain
QuantLens Production-grade local-LLM quant analyst for the B3 stock market β€” RAG + guardrails + offline evals in CI, with a measured benchmark table. GenAI / AI Eng
anchora Offline RAG over Brazilian public-law documents β€” cited answers, domain-grounded. GenAI / Retrieval
market-elt Reproducible DuckDB + dbt ELT with data-quality tests β€” end to end, zero infra. Data Eng

🧠 Background that makes me different

Psychologist β†’ full-stack founder β†’ senior data/AI engineer. MSc in Big Data & Business Intelligence. I read product, behavior and data at the same time β€” a rare combination in an engineer.

πŸ”­ Currently

Building local-first AI β€” RAG, agents and LoRA fine-tuning on local models (Ollama) β€” and reproducible data platforms, with engineering rigor (CI, tests, evals, measured results).

πŸ› οΈ Tech

Python PyTorch FastAPI LangChain Spark dbt DuckDB Docker Kubernetes AWS Azure Terraform

πŸŽ“ Certifications

Azure Data Scientist Associate (DP-100) Β· Fabric Analytics Engineer (DP-600) Β· Power BI Data Analyst (PL-300) Β· Certified Associate in Project Management (CAPM)

Open to remote opportunities β€” let's talk on LinkedIn.

Popular repositories Loading

  1. market-elt market-elt Public

    DuckDB + dbt ELT with data-quality tests β€” reproducible end to end, zero infra.

    Python

  2. anchora anchora Public

    Offline RAG over Brazilian public-law documents β€” cited, domain-grounded answers.

    Python

  3. quantlens quantlens Public

    Production-grade local-LLM quant analyst for the B3 stock market: RAG, guardrails, measured offline evals.

    Python

  4. Rodrigo-Palma Rodrigo-Palma Public

    JavaScript

  5. litellm litellm Public

    Forked from BerriAI/litellm

    Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

    Python

  6. pydantic-ai pydantic-ai Public

    Forked from pydantic/pydantic-ai

    AI Agent Framework, the Pydantic way

    Python