2 months ago
Sŏngnam, Korea, SouthMid Level
Responsibilities
- Build long-term memory, retrieval, personalization, and learning-loop systems using user experience, preferences, and context.
- Design context engineering and summarization strategies within context-window and latency constraints.
- Develop proactive agent experiences including candidate generation, ranking, conversations, notifications, reminders, and briefings.
- Design offline evaluations and online A/B experiments and establish closed-loop evaluation systems for memory, recommendations, and intervention policies.
- Experiment with current research and implement reliable production capabilities using LLMs, machine-learning and statistical models, and rule-based systems.
Requirements
- Master’s degree or higher in computer science, artificial intelligence, or a related field, plus at least four years of professional experience in AI/ML or software engineering.
- Understanding of core LLM and agentic AI principles and experience applying them to production services.
- Experience analyzing real-world logs and data to identify problems and determine improvement priorities.
- Ability to structure uncertain problems through hypothesis setting, experimentation, and evaluation.
- Software development ability to design, implement, and operate production-level AI/ML systems; Python or Kotlin is preferred.
- Ownership of important problems through user-facing outcomes and strong collaboration skills.
- Preferred experience includes long-term memory, retrieval, user modeling, personalization, recommendation systems, context-aware or proactive assistants, feedback data pipelines, ranking, contextual bandits, sequential decision-making, model training, on-device and cloud AI, privacy, and AI/LLM system optimization.
Benefits
- A three-month probationary period may apply.
- Veterans and employment-protection beneficiaries are given preference according to applicable law.
- Applicants with disabilities are given preference according to applicable law.
- The interview process includes document screening, two interviews, compensation discussion, and joining; the process may change depending on schedule and progress.
Categories
About 42dot
42dot builds software-defined vehicle and autonomous mobility platforms for automakers and mobility service providers. Its products include AI-driven vehicle software, data-based update services, and core platform components such as API gateways and identity/access management to connect services securely. The privately held company is headquartered in Seongnam-si, Gyeonggi-do, and focuses on transportation and automotive markets.