Postdoctoral Researcher

Multiagent Coordination and Verifiable Delegation

AI4I · PRAXISTurin, ItalyFull time · Two years

Call upcoming

Study how independently operated agents coordinate and delegate while preserving their commitments.

Your role

You will study the foundations of trustworthy cooperation between agents representing different principals. When agents have different information, resources and responsibilities, the behaviour of the network cannot be understood by evaluating each participant in isolation. The position offers an opportunity to investigate how useful collective behaviour can emerge while preserving the commitments under which each agent is authorised to act.

You will shape a research agenda in multiagent coordination and verifiable delegation, connecting empirical investigation with new interaction protocols, coordination methods or approaches based on learning. Central questions concern how authority should be distributed, how network structure affects cooperation, and how local guarantees relate to outcomes across the system. You will develop a focused line of research within this agenda, shaping its methods and experiments alongside colleagues with complementary expertise.

Within PC2, you will develop and test settings in which agents communicate, use resources and delegate work under explicit contracts. The research settings span central coordination, hierarchical delegation and interaction between separately operated services. You will vary topology, information, resource limits and adversarial behaviour to establish which features change safety or useful completion. You will work with the calculus team on the guarantees being tested and with engineers and empirical researchers on realistic execution.

A central aim is to distinguish failures of enforcement from undesirable outcomes despite contractual compliance, and to understand how either can propagate through an interaction network. The resulting studies will guide method development and identify limits of the current specifications. There will be opportunities to help shape an open multiagent benchmark or protocol profile and to collaborate with researchers investigating compatible systems.

Your contribution to the field

Your contribution will advance the science of coordination between agents representing different principals. By connecting interaction structure, contractual guarantees and observed network behaviour, you will develop evidence and methods for distributing authority while preserving the commitments that govern a shared task. New coordination approaches, comparative studies and open multiagent environments will establish a distinctive research contribution to trustworthy delegation across organisational boundaries.

An initial research or development direction

An example starting point is to compare delegation structures on matched tasks with explicit constraints associated with each principal, identifying which arrangements support useful cooperation and where commitments conflict. The study will test the assumptions needed for local checks to support global behaviour and inform the design of coordination methods.

Essential background

A PhD in artificial intelligence, computer science or a closely related field; the required stage of completion and formal eligibility will be specified in the final call.
Research experience relevant to multiagent systems, coordination, planning, distributed AI or rigorous experimentation with interacting agents.
Strong implementation skills and skills in experimental design, and the ability to turn a question about interactions between agents into a reproducible study.
Interest in distinct principals, delegated authority and the relationship between local agent behaviour and outcomes across the system.

Additional relevant experience

Multiagent learning, decentralised planning, negotiation, heterogeneous agents or protocol design.
Agent security, collusion or adversarial interactions, realistic benchmarks and analysis of network structure.
Formal methods, dependent type theory, compositional guarantees or proof assistants. Prior specialisation in formal methods is not required.

Candidates with depth in a relevant area and an interest in connecting it to others are encouraged to apply. Evidence of your contribution can include research papers, formal developments, substantial software or a clear account of technical work that cannot be shared publicly.

Research environment and development

Your primary supervisor will be Carlo Ciliberto. PC2 is a joint effort involving PRAXIS at AI4I, the REAL team at Bocconi and STAMP at Inria. The role requires close collaboration with the other participating groups, including opportunities for extended visiting periods at their laboratories, bringing your work into close contact with complementary expertise in machine learning, formal methods and systems.

The position is based in Turin, Italy. Remote working arrangements can be agreed when working from another laboratory in the PC2 collaboration. The timing and practical arrangements for research visits will be discussed with you and the participating hosts.

Computational resources. AI4I's HPC infrastructure provides approximately 150 NVIDIA GPUs (80 Blackwell B200 and 68 Hopper H200) and 5 PB of storage, supporting this project in agentic AI training, testing and validation.

Application materials

Please prepare:

Your CV, including relevant research or technical experience.
A short statement of fit and interests, explaining what attracts you to the role, the experience you would bring and directions you would be interested in exploring. A full research proposal is not required.
One or two representative contributions, such as papers, formal developments or software. Briefly explain your own contribution. An account of work that cannot be shared publicly is welcome; a public repository is not required.

Submission instructions and the application deadline will be published here when the call is finalised.