PhD Positions in Safe Agentic/LLM Reasoning via Formal Verification

The University of Manchester; United Kingdom; On-site; GBP 80,000 - 100,000; Full time

Job summary

A leading UK university is offering two PhD positions focusing on software verification and Large Language Model safety. Candidates should possess BSc and MSc in Computer Science or related fields, with strong backgrounds in formal methods and programming skills in C/C++ and Python. The role includes full funding and access to cutting-edge resources for impactful research in AI safety.

Benefits

Full funding including tuition fees

Competitive stipend

Access to verification infrastructure

Collaboration with leading researchers

Opportunity to contribute to open-source tools

Qualifications

• BSc and MSc in Computer Science, Mathematics, or related areas.
• Strong background in formal methods, SMT solving, abstract interpretation, or model checking.
• Experience with verification tools like ESBMC, CBMC, Z3, or similar.
• Programming proficiency in C/C++ and Python.
• Understanding of ML/NLP fundamentals and experience with transformer architectures.
• Mathematical rigor in logic, formal specifications, or constraint satisfaction.
• Excellent English communication skills (spoken and written).

Responsibilities

• Research on formal software verification and LLM safety.
• Extend automated reasoning tools to improve safety and reliability.
• Collaborate with leading researchers in formal methods and AI safety.

Skills

Formal methods

SMT solving

Abstract interpretation

Model checking

C/C++ programming

Python programming

Machine learning fundamentals

Natural language processing fundamentals

Mathematical rigor

Excellent English communication

Education

BSc in Computer Science

MSc in Computer Science

Relevant fields

Tools

ESBMC

CBMC

Z3

Clang

LLVM

Job description

Organisation/Company The University of Manchester Department Computer Science Research Field Computer science » Computer systems PhD postion Hours Per Week 35 Offer Starting Date 1 Jan 2026 Is the job funded through the EU Research Framework Programme? Horizon Europe - MSCA Is the Job related to staff position within a Research Infrastructure? No

Offer Description

We have two exciting PhD positions at the intersection of formal software verification and Large Language Model (LLM) safety, focusing on extending state-of-the-art logic-based automated reasoning tools such as ESBMC (https://github.com/esbmc/esbmc ) to address safety and reliability challenges in agentic reasoning systems.

Qualifications

• BSc and MSc in Computer Science, Mathematics, or related areas.
• Strong background in at least one of the following: formal methods, SMT solving, abstract interpretation, or model checking.
• Experience with verification tools (ESBMC, CBMC, Z3, or similar) – either academic or practical.
• Programming proficiency in C/C++, Python, and familiarity with software verification tool development.
• Understanding of ML/NLP fundamentals and experience with transformer architectures or LLM frameworks.
• Mathematical rigor in logic, formal specifications, or constraint satisfaction.
• Excellent English communication skills (spoken and written).

Specific Requirements

• Previous experience with SMT solvers (Z3, CVC5, Yices), software model checkers, or abstract interpretation tools.
• Publications in formal methods, software verification, or AI safety conferences.
• Experience with Clang, LLVM, program analysis, or compiler technologies.
• Familiarity with safety-critical systems or regulatory compliance frameworks.
• Knowledge of reinforcement learning or agent-based systems.

Languages ENGLISH Level Excellent

Research Field Computer science » Computer systems

Years of Research Experience 1 - 4

Additional Information

• Full funding including tuition fees and competitive stipend.
• Access to cutting-edge verification infrastructure and computational resources.
• Collaboration with leading researchers in both formal methods and AI safety.
• Opportunity to contribute to open-source verification tools with real-world impact.
• Industry partnerships with organizations developing safety-critical AI systems.