Jobs

GPU Software Engineer – High-Performance Kernel &Compiler Development


Job details
  • Tbwa Chiat/Day Inc
  • London
  • 1 day ago

GPU Software Engineer – High-Performance Kernel &Compiler Development London, UK About us Symbolica is an AIresearch lab pioneering the application of category theory toenable logical reasoning in machines. We’re a well-resourced,nimble team of experts on a mission to bridge the gap betweentheoretical mathematics and cutting-edge technologies, creatingsymbolic reasoning models that think like humans – precise,logical, and interpretable. While others focus on scalingdata-hungry neural networks, we’re building AI that understands thestructures of thought, not just patterns in data. Our approachcombines rigorous research with fast-paced, results-drivenexecution. We’re reimagining the very foundations of intelligencewhile simultaneously developing product-focused machine learningmodels in a tight feedback loop, where research fuels application.Founded in 2022, we’ve raised over $30M from leading Silicon Valleyinvestors, including Khosla Ventures, General Catalyst, AbstractVentures, and Day One Ventures, to push the boundaries of applyingformal mathematics and logic to machine learning. Our vision is tocreate AI systems that transform industries, empowering machines tosolve humanity’s most complex challenges with precision andinsight. Join us to redefine the future of AI by turninggroundbreaking ideas into reality. About the role As a GPU SoftwareEngineer at Symbolica, you will specialize in the design,development, and optimization of GPU kernels and algorithms tosupport the training and inference of symbolic reasoning models.You will leverage frameworks like CUDA and CUTLASS, along withcompiler optimization techniques, to push the boundaries ofperformance for high-dimensional computation. Your focus *Collaborating with mathematicians and researchers to design highlyefficient implementations of complex algorithms. * Analyzing andoptimizing GPU performance, focusing on memory management, threadutilization, compiler-generated optimizations, and computationthroughput. * Building and maintaining scalable, reusableGPU-accelerated libraries tailored for symbolic reasoningworkloads. * Profiling and benchmarking kernel performance,identifying compiler inefficiencies, and implementing solutions formaximum efficiency. About you * Strong proficiency in at least onehigh-performance programming language (C, C++, Rust, Haskell, orJulia) and familiarity with Python. * Proficiency in GPUprogramming with CUDA, including experience with kerneldevelopment, compiler optimizations, and performance tuning.Experience with CUTLASS and familiarity with tensor operations andmatrix multiplications. * In-depth knowledge of GPU architecture,including memory hierarchies, thread blocks, warps, and scheduling.Experience with compiler development, LLVM, or domain-specificlanguage (DSL) optimizations is a strong plus. * Proven experienceoptimizing numerical algorithms for high-performance computingenvironments. * Familiarity with LSP (Language Server Protocol) anda background in linear algebra, symbolic computation, or relatedmathematical fields are strong pluses. Symbolica is an equalopportunities employer. We celebrate diversity and are committed tocreating an inclusive environment for all employees, regardless ofrace, gender, age, religion, disability, or sexual orientation.Apply for this job * indicates a required field First Name * LastName * Email * Phone Resume/CV * Enter manually Accepted filetypes: pdf, doc, docx, txt, rtf Are you available to work onsite atour brand-new London office? * Select...J-18808-Ljbffr

Sign up for our newsletter

The latest news, articles, and resources, sent to your inbox weekly.

Similar Jobs

Software Engineer (ML Infra) (Hiring Immediately)

About the jobAdamas Knight is recruiting for a groundbreaking AI Lab, backed by some of the biggest names in industry, working on building their own proprietary foundation model within the multi-modal domain - text and vision.With one of the best compute in industry, they are looking for a ML Infrastructure...

Adamas Knight London

Principal Software Engineer

Principal Compute Software Engineer – AI EdgeLocation:Remote in UKJob Type:Full-timeAbout the Company:A leading organisation in AI infrastructure is developing cutting-edge compute software to enhance AI and machine learning applications. The team specialises in high-performance solutions that optimise AI workloads on next-generation hardware.The Role:The company seeks aPrincipal Compute Software Engineer –...

IC Resources Cambridge

Machine Learning Engineer for Game Technology (Basé à London)

Why PlayStation?PlayStation isn't just the Best Place to Play - it's also the Best Place to Work. Today, we're recognized as a global leader in entertainment producing The PlayStation family of products and services including PlayStation5, PlayStation4, PlayStationVR, PlayStationPlus, acclaimed PlayStation software titles from PlayStation Studios, and more.PlayStation also strives...

Jobleads London

Performance Analysis Engineer

About the roleWe are seeking a highly skilled and motivated Performance Analysis engineer to join our diverse team at Arm! Our team focuses on Performance Analysis of Arm based automotive systems build together in pre-silicon (Virtual Prototypes & FPGAs) and postsilicon environments!Make sure to apply with all the requested information,...

ARM Farnham

Software Engineers (C++/QT or C#/WPF)

Software Engineers (C#/WPF Or C++/QT)Do you have the right skills and experience for this role Read on to find out, and make your application.Guildford, Surrey£60000 - £90000 + 25% Bonus, 10% Pension, Private Medical.- Eligible to work in the UK without Visa Sponsorship.- A Masters or PhD Degree in Engineering,...

Hays Technology Guildford

C++ Engineer – World’s Largest (Almost!) Supercomputer

Do you want to work on some of the most advanced technology in the world?Our client operates one of the most powerful private HPC clusters globally, with 10s of thousands of GPUs (including 1000s of A100s), 100s of petabytes of storage, and almost 10 petabytes of RAM. This cutting-edge infrastructure...

Augmentti London