Postdoctoral Researcher position in Neuro-Symbolic Agentic / LLM Reasoning F / M

Job Description

The Neuro-Symbolic AI Group at the IDIAP Research Institute operates at the interface between neural and symbolic AI methods aiming to enable the next generation of explainable, data-efficient and safe AI systems. Our research investigates how the combination of latent and explicit data representation paradigms can deliver better learning and reasoning over data.

We are looking for a Postdoctoral Researcher for an initial project of months (extendable depending on funds).

In partnership with a leading company in the field of Hardware verification, we aim to develop a neuro-symbolic AI platform to convert informal digital design specifications into formally checkable verification artifacts, with logical rigor, traceability, and iterative validation. The project combines the generalization capabilities of large language models with symbolic constraints and formal verification backends to ensure generated properties are auditable, consistent, and correct-by-construction (or corrected via proof / counterexample feedback).

You will lead research and prototyping of neuro-symbolic methods that translate heterogeneous requirements (text, tables, diagrams) into structured representations and formally checkable properties. This includes designing controlled reasoning pipelines that combine LLMs with symbolic constraints (typed logical forms, DSL / IR design, constrained decoding), integrating formal feedback loops (SAT / SMT / model checking, counterexample- and proof-guided refinement), and developing mechanisms for semantic consistency, assumption management, and end-to-end traceability from specification fragments to generated SVAs and solver outcomes.

You will also help define benchmarks and evaluation protocols (correctness, robustness, coverage), publish at top-tier AI / ML venues, and contribute high-quality research code.

Profile

This is an exciting opportunity for candidates who would like to work on the foundations of agentic reasoning, in close dialogue with complex real-world problems.

Essential requirements :

PhD (or near completion) in AI / ML / NLP, Computer Science, or related

Strong research track record in neuro-symbolic AI / verifiable reasoning, demonstrated by publications and / or impactful preprints / software Experience with at least one of :

• . LLMs for structured reasoning (autoformalization, program synthesis, semantic parsing, tool-augmented / agentic workflows)
• . Symbolic methods (logic / constraints, SAT / SMT, theorem proving, planning)

Strong software engineering skills (typically Python)

About Idiap

Idiap is a research institute of national importance that engages in fundamental research, education, and technology transfer in artificial intelligence. PhD students are formally registered at EPFL, one of the leading Technical Universities in Europe.

Idiap offers competitive salaries and conditions in a dynamic and multicultural environment. Idiap is located in Martigny, Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exceptional quality of life, exciting recreational activities, including hiking, climbing, and skiing, as well as varied cultural activities. English is the official working language.

At Idiap we place great emphasis on diversity, and we know diversity fosters creativity and innovation. We are committed to equality of opportunity, to being fair and inclusive, and to being a place where we all belong. Employment at Idiap is based solely on a person's merit and qualifications.

Required languages