Pica Code IR-2026-112 Composable Policy for Multi-Objective Optimization in World Models

Italian Ministry of Education, University and Research

Italy

On-site

EUR 60,000 - 75,000

Full time

3 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Unimore in Italy invites applications for a recognised researcher position focused on research and implementation of composable policies for multi-objective optimization in World Models (model-based reinforcement learning). The role aims to combine policies learned on separate objectives at inference time without retraining.

The successful candidate will engage in selective procedures based on qualifications and interview; country/ies of residence: OTHER.

Qualifications

  • Experience in research on reinforcement learning and policy optimization.
  • Familiarity with model-based approaches and world models is desirable.

Responsibilities

  • Research and implement composable policies for multi-objective optimization in World Models.
  • Explore objective trade-offs and task arithmetic in weight space for inference-time deployment.

Skills

World Models
Composable policies
Multi-objective optimization
Reinforcement learning
Model-based RL

Job description

Organisation/Company Unimore Research Field Engineering » Industrial engineering Researcher Profile Recognised Researcher (R2) Leading Researcher (R4) First Stage Researcher (R1) Established Researcher (R3) Application Deadline 25 Nov 2026 - 13:00 (UTC) Country Italy Type of Contract To be defined Job Status Not Applicable Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Research and implementation of composable policies for multi-objective optimization in World Models (model-based reinforcement learning), aiming to combine at inference time, without retraining, policies and skills learned on individual objectives, also through task arithmetic in weight space, so as to obtain different trade-offs among conflicting objectives.

  • Italy

Eligibility of fellows: country/ies of residence:

  • OTHER

Eligibility of fellows: nationality/ies:

  • OTHER
Selection process

selective public procedure based on qualifications and interview

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

World Models: Multiobjective Policy Composer
World Models: Multiobjective Policy Composer

Italian Ministry of Education, University and Research • Italy

On-site
EUR 60,000 - 75,000
Pica Code IR-2026-106 Efficient multimodal foundation models: optimization, compression and transfer to the services of the Italian AI Factory
Pica Code IR-2026-106 Efficient multimodal foundation models: optimization, compression and transfer to the services of the Italian AI Factory

Italian Ministry of Education, University and Research • Italy

On-site
EUR 38,000 - 56,000
Pica Code IPD-2026-060 Multimodal Foundation Models and Retrieval-Augmented Generation
Pica Code IPD-2026-060 Multimodal Foundation Models and Retrieval-Augmented Generation

Italian Ministry of Education, University and Research • Italy

On-site
EUR 35,000 - 55,000
Pica Code IR-2026-103 Advanced Methodologies for Dynamic GPU Resource Management in Embedded Systems
Pica Code IR-2026-103 Advanced Methodologies for Dynamic GPU Resource Management in Embedded Systems

Italian Ministry of Education, University and Research • Italy

On-site
EUR 36,000 - 55,000
Pica Code IPD-2026-063 Energy-based Methods for control and safety of a robotic system
Pica Code IPD-2026-063 Energy-based Methods for control and safety of a robotic system

Italian Ministry of Education, University and Research • Italy

On-site
EUR 35,000 - 52,000
Pica Code Ir-2026-095 Methods And Tools For The Security, Privacy, And Resilience Of Communications In Cooperative Intelligent Transportation Systems
Pica Code Ir-2026-095 Methods And Tools For The Security, Privacy, And Resilience Of Communications In Cooperative Intelligent Transportation Systems

Italian Ministry Of Education, University And Research • Italy

On-site
EUR 30,000 - 42,000
Pica Code IR-2026-111 Research and development of perception and planning algorithms for autonomous driving in mining environments.
Pica Code IR-2026-111 Research and development of perception and planning algorithms for autonomous driving in mining environments.

Italian Ministry of Education, University and Research • Italy

On-site
EUR 30,000 - 38,000
Pica Code IR-2026-109 Development of Advanced Life Cycle Assessment and Life Cycle Costing Models and Tools for the Environmental Characterization of Products, Processes, Services or Organizations
Pica Code IR-2026-109 Development of Advanced Life Cycle Assessment and Life Cycle Costing Models and Tools for the Environmental Characterization of Products, Processes, Services or Organizations

Italian Ministry of Education, University and Research • Italy

On-site
EUR 30,000 - 42,000
Pica Code IR-2026-114 - Development of control algorithms and experimental validation for legged robotic systems
Pica Code IR-2026-114 - Development of control algorithms and experimental validation for legged robotic systems

Italian Ministry of Education, University and Research • Italy

On-site
EUR 42,000 - 48,000
\"Uist - User Interface Software And Technologies\" (Cup B53C23004120005) E \"Hhpc - Horizon Hpc\" (Cup B53C24000890005) - Bando Cr 007 2026 Isti Pi
\"Uist - User Interface Software And Technologies\" (Cup B53C23004120005) E \"Hhpc - Horizon Hpc\" (Cup B53C24000890005) - Bando Cr 007 2026 Isti Pi

Italian Ministry Of Education, University And Research • Italy

On-site
EUR 40,000 - 60,000