Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am an AI/ML Engineer and full-stack developer focused on building and deploying end-to-end AI-driven web applications. I work with Python, FastAPI, TypeScript, and modern frontend frameworks, with strong expertise in LLM pipelines and AI agent orchestration (LangGraph). I translate complex AI concepts into user-friendly products for non-technical stakeholders and enjoy delivering scalable, production-ready solutions. A notable achievement in my career is achieving a 41% latency reduction on a banking LLM summarization pipeline, delivering meaningful impact for a major financial institution and stakeholders.…I am an AI/ML Engineer and full-stack developer focused on building and deploying end-to-end AI-driven web applications. I work with Python, FastAPI, TypeScript, and modern frontend frameworks, with strong expertise in LLM pipelines and AI agent orchestration (LangGraph). I translate complex AI concepts into user-friendly products for non-technical stakeholders and enjoy delivering scalable, production-ready solutions. A notable achievement in my career is achieving a 41% latency reduction on a banking LLM summarization pipeline, delivering meaningful impact for a major financial institution and stakeholders.

Pietro Ruzzante

Data Scientist, Full Stack Developer, AI Engineer, +2





I am an AI/ML Engineer and full-stack developer focused on building and deploying end-to-end AI-driven web applications. I work with Python, FastAPI, TypeScript, and modern frontend frameworks, with strong expertise in LLM pipelines and AI agent orchestration (LangGraph). I translate complex AI concepts into user-friendly products for non-technical stakeholders and enjoy delivering scalable, production-ready solutions. A notable achievement in my career is achieving a 41% latency reduction on a banking LLM summarization pipeline, delivering meaningful impact for a major financial institution and stakeholders.…I am an AI/ML Engineer and full-stack developer focused on building and deploying end-to-end AI-driven web applications. I work with Python, FastAPI, TypeScript, and modern frontend frameworks, with strong expertise in LLM pipelines and AI agent orchestration (LangGraph). I translate complex AI concepts into user-friendly products for non-technical stakeholders and enjoy delivering scalable, production-ready solutions. A notable achievement in my career is achieving a 41% latency reduction on a banking LLM summarization pipeline, delivering meaningful impact for a major financial institution and stakeholders.

Available to hire

I am an AI/ML Engineer and full-stack developer focused on building and deploying end-to-end AI-driven web applications. I work with Python, FastAPI, TypeScript, and modern frontend frameworks, with strong expertise in LLM pipelines and AI agent orchestration (LangGraph). I translate complex AI concepts into user-friendly products for non-technical stakeholders and enjoy delivering scalable, production-ready solutions.

A notable achievement in my career is achieving a 41% latency reduction on a banking LLM summarization pipeline, delivering meaningful impact for a major financial institution and stakeholders.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

Italian

Fluent

English

Advanced

Spanish; Castilian

Advanced

Work Experience

Machine Learning Engineer at Multiverse Computing

January 1, 2026 - Present

Design and deployment of end-to-end AI-driven web applications (Python, FastAPI, TypeScript) for enterprise clients, from backend LLM pipelines to user-facing interfaces. Built and deployed an end-to-end LLM-based document summarization system for a major Spanish financial institution using a Python backend with FastAPI, a map-reduce architecture, quantized LLM inference, and an interactive evaluation dashboard. Collaborated with client stakeholders to translate requirements into production-ready deliverables. Key Achievement: 41% reduction in latency of the LLM summarization pipeline. Foundry – AI Agent Platform: designed evaluation and observability APIs (LangGraph + FastAPI) for LLM-as-judge metrics, online sampling, and regression tests exposed as reusable endpoints in the shared agentkit library, ensuring code quality and scalability.