h3Mission /h3 pThe Keystone project, an ARIA-funded collaboration between EPFL and Imperial College London, aims to build a formally-verified ML inference engine, demonstrating that AI can help make verified systems competitive with unverified systems in terms of development effort, features, and performance. Its missions include the design and implementation of verified inference components, the formalization of GPU kernel semantics, the development of AI-assisted proof engineering workflows, and the open-source release of specifications, proofs, and verified artefacts. /p h3Mission /h3 pThe Keystone project, an ARIA-funded collaboration between EPFL and Imperial College London, aims to build a formally-verified ML inference engine, demonstrating that AI can help make verified systems competitive with unverified systems in terms of development effort, features, and performance. Its missions include the design and implementation of verified inference components, the formalization of GPU kernel semantics, the development of AI-assisted proof engineering workflows, and the open-source release of specifications, proofs, and verified artefacts. We seek an excellent software engineer to play a central role in turning verified research prototypes into a production-grade, high-performance inference engine. Prior experience with formal verification is welcome but not required: a strong systems engineer with the motivation to learn proof-assistant technology will thrive in this role. /p h3Main Duties And Responsibilities /h3 ul liBring technical expertise in systems programming and performance engineering to support the project’s research; collaborate with the research teams at EPFL and Imperial College London /li liDesign, implement, and maintain core components of the verified LLM inference engine, including the runtime and glue code connecting extracted verified code, GPU kernels, and drivers /li liOrganize and manage the project’s engineering infrastructure: differential testing against reference engines (vLLM, SGLang), continuous integration for code and proofs, and performance benchmarking /li liDevelop and maintain agentic AI pipelines for specification autoformalization, proof generation, and proof repair /li liWrite documentation, procedures, and recommendations to ensure reproducibility of the project’s artefacts /li liDiagnose, prevent, and repair failures and regressions across the software stack /li liAnalyze the security level and trusted computing base of the components we develop, and contribute to red/blue team exercises within the ARIA programme /li liContribute to open-source releases and engage with their user communities /li /ul h3Profile /h3 ul liHigher degree in computer science or education deemed equivalent; experience in the field /li liExcellent technical knowledge of systems programming, and strong programming ability in several of: Python, C/C++, Rust, OCaml, or other functional languages /li liKnowledge of one or more of the following, with strong motivation to grow in the others: ul liGPU programming (CUDA, Triton, PTX) or high-performance computing /li liML inference or serving systems (vLLM, SGLang, PyTorch internals, or similar) /li liInteractive theorem proving (Rocq, Lean, HOL, Isabelle, or similar) or other formal methods /li /ul /li liExperience maintaining development tooling: build systems, continuous integration, and test infrastructure /li liExperience using LLM-based development tools or building agentic workflows is a plus /li liMastery of English indispensable (oral and written); French is an asset but not required /li liSense of priorities, integrity, and autonomy in your work /li liTeam spirit and aptitude for conducting technical investigations and implementations; excellent ability to communicate with varied audiences, from proof engineers to systems researchers /li liStrong sense of service and spirit of initiative /li /ul h3We offer /h3 ul liThe possibility to join a dynamic and stimulating team on a high-profile ARIA-funded project /li liA multicultural and academic working environment of high quality /li liOpportunities for continuing education and professional development /li liExcellent working conditions /li liGenerous access to frontier AI models and high-performance compute /li liFunded travel for collaboration between Lausanne and London, and for conferences /li /ul pFor any further information, please contact: Nate Foster ( ). /p pMore information can be found on /p pContract Start Date : , or to be determined /p pActivity Rate: 100.00 /p pContract Type: CDD /p pDuration: 1 year, renewable (project duration permitting) /p pReference: 2477 /p #J-18808-Ljbffr
Software Engineer: Keystone Project (Machine-Verified LLM Inference) in Lausanne Arbeitgeber: EPFL
Das AGORA Cancer Research Center der EPFL in Lausanne bietet eine inspirierende Arbeitsumgebung, die sich durch eine kollaborative und interdisziplinäre Kultur auszeichnet. Als Labor-Techniker im Bereich Krebsforschung und Immunologie haben Sie die Möglichkeit, an bedeutenden Forschungsprojekten zu arbeiten und Ihre Fähigkeiten in einem dynamischen Team weiterzuentwickeln. Zudem profitieren Sie von umfangreichen Weiterbildungsmöglichkeiten und einem engagierten Netzwerk von Fachleuten, die gemeinsam an der Bekämpfung von Krebs arbeiten.
