Impress employers and recruiters.
Choose from hundreds of resume examples.

Target Resume Now

Tailor your resume to this Research Engineer / Research Scientist, Zero-Knowledge Verification role.

Rezi rewrites your resume against Singapore AI Safety Hub's job description. Free.

Resume score gauge reading 58 out of 100

Don't guess if your resume is good enough.

See how it scores against the Research Engineer / Research Scientist, Zero-Knowledge Verification posting at Singapore AI Safety Hub — free, in seconds.

About the Role

The Verification team builds and tests tools to verify agreements about AI, prototyping new mechanisms, leading international research collaborations, and working with policymakers. This role is crucial for ensuring the trustworthy adoption of AI in high-stakes industries and enabling international cooperation.

Responsibilities

Drive down proving cost.
Close the gap between current proof capabilities and frontier inference requirements.
Develop a system that skeptical adversaries' technical staff would approve.
Collaborate with hardware-security and systems colleagues.
Work with external cryptographers.
Publish research findings.
Prove a full inference transcript from a frontier-scale model end to end and report its cost.
Bring an open prototype to parity with the best proprietary systems.
Make the state of the art public and checkable.
Close out the data-preparation path dominating current proving time.
Use the reference-implementation check as a correctness oracle for AI-assisted optimization.
Help develop the future research agenda for this field.
Design and analyze sub-sampling schemes for bounding information a dishonest prover can smuggle.
Integrate exact emulation of hardware's floating-point behavior into ZKPs.
Move production inference to integer arithmetic with batch-invariant kernels.
Build proof circuits for low-precision formats like NVFP4.
Investigate compute- and memory-exhaustion schemes.
Hide model architectures using proof recursion.
Red-team the constraint system.

Requirements

Built something real with a modern proof system (Halo2, Plonky3, STARK-based stacks, or comparable) or have deep GPU and ML systems experience and want to learn proof systems on the job.
Comfortable reasoning about soundness, adversary capabilities, assumption validity, and critical argument points.
Ability to write code that others will attack.
Willingness to handle the 'unglamorous last mile' of generalization, numerical mismatches, rather than only the 'interesting part'.
Thrive in ambiguous, early-stage environments where problem definition is part of the job.
Published work in applied cryptography, verifiable computation, or succinct proofs (strong candidate).
Low-precision numerics experience (strong candidate).
Formal verification experience, especially of a verifier codebase or protocol (strong candidate).
Familiarity with lookup arguments, recursion, or folding schemes (strong candidate).
Experience explaining a cryptographic guarantee to a non-expert (strong candidate).
Experience using AI systems as research collaborators on checkable correctness problems, with a view on their applicability (strong candidate).

Skills

Modern proof systems (Halo2, Plonky3, STARK-based stacks)
GPU systems
ML systems
Soundness reasoning
Code writing
Generalization
Numerical analysis
Applied cryptography
Verifiable computation
Succinct proofs
Low-precision numerics
Formal verification
Lookup arguments
Recursion
Folding schemes
Cryptographic guarantee explanation
AI systems as research collaborators

Location

Remote

Work Type

Full-time

Experience Level

Early career researcher
Production proof system shipper

About the Company

SASH's mission is to build tools that can earn trust across borders, addressing the urgent technical and political challenge of verifying what is happening inside AI datacenters.
The Verification team combines technical expertise with international AI policy experience.
The team has leadership from an Associate Professor at University of Birmingham and experience from the Singapore Government.
The policy team has experience from Oxford and the Centre for the Governance of AI.
Partners include experts from the Future of Life Institute and the University of Oxford.