AI Engineer - Reinforcement Learning

Job DescriptionAt Logical Intelligence, we're revolutionizing software development with AI-powered formal verification. We've developed groundbreaking agents that provide mathematical guarantees of code correctness, ensuring that software behaves exactly as intended while proactively identifying bugs and security vulnerabilities. Our novel foundation model enables scalable, precise reasoning for formally verifiable code across Rust, Golang, and smart contract VMs. We’ve won a well-known formal verification benchmark called PutnamBench, which consists of 672 hard math problems from the William Lowell Putnam Exam, the oldest collegiate mathematics competition in North America. Backed by a world-class team – including ICPC champions, a Fields Medalist and an ACM Turing Award winner – we're building the future where all code is provably correct.About the roleJoin our team as an AI Engineer and help us push the boundaries of what's possible in logical reasoning! We’re looking for a motivated individual to design, implement, and refine efficient Large Language Models (LLMs) pipelines for scaled distributed training. You'll be at the forefront of designing and refining algorithms that go beyond the capabilities of traditional LLMs. You'll work closely with a talented team of AI experts, EBM specialists, formal verification engineers, and software developers to create groundbreaking solutions.What you'll doImplement new reasoning algorithms and modelsEvaluate reasoning approaches, including latent space reasoningPre-train, fine-tune, and modify the State-of-the-Art LLMsOptimizing and scaling LLM pipelinesAdjust frameworks and interfaces to accelerate machine learning developmentDerive practical solutions and integrate them with the results of other teams to provide the best overall resolutionQualificationsDeep understanding of transformers' internals, and ability to make radical changes to the architecture and handle higher-order derivativesExpertise in programming languages and tools critical for high-performance computing in Python/C++ and machine learning including Deep Learning frameworks like PyTorch /TensorFlow/JAXExpertise in optimizing machine learning systems, including general techniques and LLM-specific optimizationsUnderstanding state-of-the-art approaches in LLM reasoningAbility to understand complex learning approaches, such as energy-based modelsExperience with basic distributed optimization techniquesFamiliarity with torch.compile or similar performance optimization toolsUnderstanding of LLM architectures and LLM fine tuning internals3+ years of production experience in ML Infra, DataOps, distributed training. Proficiency with Kubernetes clusters and distributed compute assetsStrong communication and teamwork skillsReadiness to explore and promote cutting edge technologies in ML Infrastructure domain and beyondBonus Points:Demonstrated publications in any of the major conferencesExperience in EBM or latent reasoningDemonstrated publications in any of the major conferencesMathematical Reasoning – discrete math and logic