Skip to content
View sebtosca's full-sized avatar
🤖
🤖
4 followers · 14 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report sebtosca

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
sebtosca/README.md

Sebastien Toscano

AI Engineer

Building production-ready AI systems, RAG pipelines, and agentic workflows.

Tech Stack

AI / LLM

Python PyTorch LangChain LangGraph HuggingFace Agentic AI

Backend / Infrastructure

TypeScript FastAPI Docker Kubernetes Apache Airflow Apache Spark Redis PostgreSQL Elasticsearch Linux AWS GCP

Retrieval / Evaluation / Observability

Qdrant LangSmith OpenTelemetry RAGAS Prometheus

Current Focus (July 2026)

  • Agentic AI systems (MAS) with RL policy optimization (ex: off-policy learning, exploration, credit assignment)
  • DSA & System Design
  • ETL Pipelines & Search Indexing (Spark, Elasticsearch)

Paper to read for this week (July):

Featured Repositories

Connect

Build fast. Ship real systems.

Pinned Loading

  1. AI-Financial-Research-Agent AI-Financial-Research-Agent Public

    Autonomous financial research agent combining live market data, financial news, sentiment analysis, and private RAG with transparent execution.

    Python 1

  2. cortex-retrieval-platform cortex-retrieval-platform Public

    Production-ready retrieval platform for AI systems, combining hybrid search, semantic ranking, and scalable RAG pipelines for intelligent knowledge access.

    Python 1

  3. autogam-research autogam-research Public

    Research repository for AutoGAM, an automated extension of Generalized Additive Models for interpretable, reproducible tabular regression with interaction discovery and runtime-aware benchmarking.