Lorenzo Satta Chiris: AI Safety Research and Engineering Expertise

Lorenzo Satta Chiris is a multi-award-winning AI researcher, engineer, and entrepreneur dedicated to making AI safe and trustworthy. Specialising in agent autonomy, risk assessment, and alignment, he develops frameworks, educational programs, and tools to ensure human control over AI systems. He is a Global Excellence Engineering and Entrepreneurship scholar at the University of Exeter, where he co-developed the AURA framework for quantifying and monitoring AI agent autonomy. Lorenzo has also architected and deployed guardrailed multi-agent systems in production through his role as CTO of Oorbital.

AI Safety Research and Engineering Services

Lorenzo Satta Chiris offers specialised expertise at the intersection of AI research, engineering, and education. His work focuses on ensuring that AI systems, particularly autonomous agents, are developed and deployed in a manner that prioritises human safety and control. This includes theoretical research, practical engineering solutions, and educational initiatives to foster a deeper understanding of AI safety principles.

Agent Autonomy and Risk Assessment

Lorenzo's research delves into the complexities of agent autonomy, aiming to quantify and manage the associated risks. He co-developed the AURA (Agent Autonomy Risk Assessment) framework, a mathematical model designed to assess and monitor the autonomy levels of AI agents. This framework is crucial for understanding the potential risks posed by increasingly independent AI systems and for developing appropriate safety guardrails. The AURA framework was presented at MLCon Amsterdam in 2026.

Guardrailed Multi-Agent Systems

As CTO of Oorbital, Lorenzo architects and deploys guardrailed multi-agent systems in real-world applications. These systems integrate advanced techniques like Retrieval-Augmented Generation (RAG) pipelines, LLM orchestration, and robust safety guardrails to ensure AI agents operate within defined ethical and operational boundaries for industry clients. This practical application of AI safety principles helps businesses leverage advanced AI while mitigating potential risks.

Education and Knowledge Dissemination

Lorenzo is committed to educating a broad audience on AI safety and development. Through his blog, which has reached over 200,000 tech enthusiasts globally, he translates complex AI research into accessible insights for practitioners, educators, and the public. He also leads large-scale educational initiatives, such as directing the world's largest student-led coding and AI bootcamps (ExCode), which has involved over 2,500 participants and earned Tech South West's Best & Most Innovative Organisation award.

Speaking and Consulting Engagements

Lorenzo is a sought-after speaker, having delivered over 46 talks at major conferences and events, including Google DevFest, Microsoft Azure AI Connect, and the Dutch AI Conference. His presentations cover topics such as agentic systems in production, human-AI interaction design, and the ethical considerations of advanced AI. He also offers technical consulting services, advising organisations on building safe and useful AI systems.

What Lorenzo Satta Chiris Offers

Lorenzo Satta Chiris provides a comprehensive suite of services and expertise in AI safety and engineering. His offerings are designed to address the critical challenges of developing and deploying AI responsibly, with a focus on ensuring human control and mitigating risks associated with advanced AI systems.

Frequently Asked Questions

What is Lorenzo Satta Chiris's primary area of expertise?

Lorenzo Satta Chiris is an AI researcher and systems engineer specializing in agent autonomy, multi-agent orchestration, and AI alignment. His work focuses on developing frameworks, education, and tools to ensure that AI systems remain safe and controllable by humans.

What is the AURA framework?

The AURA framework, co-developed by Lorenzo Satta Chiris, is a risk assessment model designed to quantify and monitor the autonomy of AI agents. It helps in understanding and managing potential risks associated with AI systems that operate with increasing independence.

What kind of practical AI systems does Lorenzo Satta Chiris build?

Lorenzo, as CTO of Oorbital, architects and deploys guardrailed multi-agent systems for industry clients. These systems incorporate features like RAG pipelines and LLM orchestration, all integrated with safety guardrails to ensure responsible operation.

How does Lorenzo Satta Chiris contribute to AI education?

Lorenzo directs ExCode, the UK's largest student-led coding and AI bootcamp, and has developed AI skills programmes for university students. He also shares knowledge through his blog, making complex AI research accessible to a wide audience.

What awards and recognition has Lorenzo Satta Chiris received?

Lorenzo is a multi-award-winning developer and engineer. He received Tech South West's Best & Most Innovative Organisation award for his work with ExCode, and has been recognised with numerous other accolades and scholarships for his contributions to AI and entrepreneurship.

How can one collaborate with Lorenzo Satta Chiris on research or consulting?

Collaboration inquiries for research, speaking engagements, or technical consulting can be made via direct email to ls1044@exeter.ac.uk or through his LinkedIn profile.

Contact Lorenzo Satta Chiris

For collaboration on AI safety research, speaking invitations, technical consulting, or general inquiries, please reach out via the following: