Skip to content
View cchinchilla-dev's full-sized avatar

Block or report cchinchilla-dev

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.

Content in all repositories owned by your account will be closed.
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
cchinchilla-dev/README.md

Carlos Chinchilla Corbacho

ML ENGINEER · PHD CANDIDATE ON TESTING LLM AGENTS

cchinchilla.dev · ORCID · Scholar · LinkedIn · Substack


BACKGROUND

PhD candidate at the University of Salamanca, researching the testing of LLM-based and multi-agent systems. ML engineer in industry. Trust, but Trace covers the engineering side of that work: what survives between research papers and production systems.

PROJECTS

Open-source tools

For evaluating and orchestrating ML systems, and the tooling around the work.

2026 agentanvil — contract-driven testing for LLM-based and multi-agent systems. Portable across runtimes. In development
2026 agentloom — deterministic LLM workflow orchestration. You define the execution graph; the model only fills in content. In development
2026 swiftbar-devkit — four macOS menu bar tools. No daemon, no telemetry, one config file. Alpha
2024 vocal-biomarkers-ml — reproducible ML pipeline for respiratory-disease detection from voice. Archived

OPEN SOURCE

Contributions

Patches, primitives, and bug reports across the agent-tooling ecosystem.

2026 a2aproject/a2a-python — standardised async client lifecycle, JSON canonicalisation fix (RFC 8785) for cryptographic signatures. Contributor
2026 a2aproject/a2a-go — REST streaming error alignment with JSON-RPC and gRPC, executable documentation validated by go test. Contributor

PUBLICATIONS

Peer-reviewed work

Batteries, IEEE Access, and a Springer chapter. Full record on ORCID.

2025 Advanced Machine Learning and Deep Learning Approaches for Estimating the Remaining Life of EV Batteries — A Review
Batteries
Paper
2024 Application of Machine Learning Techniques for the Characterization and Early Diagnosis of Respiratory Diseases such as COVID-19
IEEE Access
Paper
2024 From Waste to Wealth: Circular Economy Approaches for Recycled EV Batteries in Energy Storage
New Trends in Disruptive Technologies, Tech Ethics, and Artificial Intelligence
Chapter
2024 Automated Identification of Cylindrical Cells for Enhanced State of Health Assessment in Lithium-Ion Battery Reuse
Batteries
Paper

Pinned Loading

  1. agentanvil agentanvil Public

    Contract-based testing for LLM agents: hybrid evaluation, multi-agent + A2A, deterministic replay.

    Python

  2. agentloom agentloom Public

    Deterministic LLM workflow orchestration with native observability, resilience, and cost control.

    Python 4