Job Opportunities API

"Conquering cancer through AI" Lunit, a portmanteau of ‘Learning unit,’ is a medical AI software company devoted to providing AI-powered total cancer care. Our AI solutions help discover cancer and predict cancer treatment outcomes, achieving timely and individually-tailored cancer treatment. 🗨️ About the Team Who will I spend 8+ hours/day with? You will join the AI Innovation team behind the Chain-of-Evidence (CoE) project, also known as 특화 파운데이션 모델 project. The team brings together AI research scientists and engineers across RAG & Product, Model & Evaluation, and Data & Knowledge, building real products while tackling meaningful applied research along the way. Members have diverse backgrounds and interests — some are passionate about LLM training and evaluation, others about retrieval and knowledge systems, others about productization and clinical deployment — united by a shared commitment to improving patient care. This team is a fast paced “full stack” team, where ideation to deployable PoC happens in rapid iteration cycles. The team gets to work on strategically important initiatives aligned to enabling new business opportunities for Lunit. 🗨️ About the Position What will make me proud to work here? You will have a direct impact on bringing trustworthy, evidence-grounded AI into real clinical workflows — clinical intelligence and agentic applications — deployed and evaluated together with partner hospitals. Your work will push forward the performance of Lunit's medical foundation models, RAG systems, and agentic pipelines that power the Lunit’s next generation clinical intelligence. We work with large-scale clinical knowledge sources (medical literature, clinical guidelines, insurance and EMR data) and the cloud/GPU compute to leverage them. Current work spans LLM post-training (SFT/SDFT), retrieval-augmented generation, agentic reasoning, faithfulness and citation evaluation, and live clinical deployment — among others. Experience personal and professional growth by working on diverse projects, collaborating with talented multi-disciplinary teams and meeting actual medical professionals who will be using our systems. 🚩 Roles & Responsibilities Propose, design, and implement components of “Clinical Intelligence”: medical foundation models, LLM- and retrieval-based AI systems that address real-world clinical problems. Build and improve the core components of ‘Clinical Intelligence’ — medical RAG, agentic reasoning pipelines, context management, LLM post-training (SFT/SDFT/RL), and rigorous evaluation of faithfulness, citation quality, and hallucination. Design and maintain the context layer that powers our agents — structuring, retrieving, and managing the knowledge and state that large-context LLM systems depend on (context engineering / context management). Collaborate with clinical partners (hospitals, medical doctors) and product teams to translate research into deployed systems clinicians actually use. Contribute to internal research codebases with high-quality code and rigorous development standards. Mentor junior researchers and actively contribute to the team's technical growth. Requirements 🎯 Qualifications 5+ years of industry/research experience in machine learning or deep learning (Master's + 4 years or PhD + 1 year), with a preference for natural language processing, large language models, information retrieval, or medical AI. Strong working knowledge of contemporary LLM, NLP, and retrieval techniques, and relevant software frameworks and libraries (e.g., PyTorch, Hugging Face Transformers, vLLM, and RAG frameworks such as LlamaIndex or LangChain) Proven ability to identify high-impact research problems and translate them into deployable ML/LLM solutions Taste for automation with harness engineering. ‘Bias towards action’ — a strong builder instinct; you turn id