About Us

Data Scientist (all genders)

Key Responsibilities

• Context/ Prompt Engineering: Design and iterate on complex LLM prompts (e.g., Chain-of-Thought, few-shot learning) to reliably extract defined entities (e.g., Symptoms, Anatomy, Drugs) and learning relationships from unstructured medical textbooks and transcripts.
• Graph Construction & Schema Definition: You will define the semantic schema and populate the chosen Graph Database (e.g., Neo4j/Cypher) to connect extracted medical facts directly to learning objectives (e.g., USMLE Step 1 goals).
• Validation Pipelines: Design and implement automated "judge" loops where an LLM or other automated checks evaluate the accuracy and logical consistency of its own extracted graph against gold-standard medical guidelines and our internal knowledge base.
• Evaluating AI features: Designing evaluation frameworks to assess an agent's performance, safety, and efficiency. This can involve measuring task completion success rates, the quality of the agent's reasoning steps, and its ability to recover from errors.
• Collaboration: Work with medical experts to validate extraction accuracy and partner with the platform engineering team to integrate the resulting Knowledge Graph API into our core product features.

Your profile

• Python Proficiency: You write clean, scalable, and modular code, understanding software engineering principles beyond one-off Jupyter Notebooks.
• LLM Experience: You have hands-on experience working with APIs from leading LLM providers.
• Structured Data Mindset: You possess a strong understanding of why data structures are critical for machine consumption, as opposed to relying on unstructured text output.
• Knowledge of or Willingness to Learn Graph DBs: You may not know Neo4j or Cypher yet, but you demonstrate exceptional enthusiasm and aptitude to master graph database technologies within your first month.
• Cloud & MLOps Familiarity: Knowledge of cloud platforms (AWS, Azure, GCP) and MLOps practices (CI/CD pipelines, containerization with Docker, monitoring tools) for deploying and productionizing AI applications.
• A Bachelor’s degree in Mathematics, Statistics, Computer Science, Economics or a similar program.
• Demonstrated impact and scope in your previous roles (e.g., creating scalable solutions, influencing product direction, etc.).

• Familiarity with medical terminologies and taxonomies (MeSH, SNOMED, ICD-10).
• A proven interest in Pedagogy, Learning Science, or Adaptive Learning Systems.
• Previous experience defining or modeling relational data schemas.

What we offer

• Flexible working hours and remote work are a given to enable you to achieve a good work-life balance.
• You are part of a highly engaged, motivated, and professional Development team.
• Your ideas are heard: We value employees who drive change with creativity. Because only with a diverse team and fresh ideas can we make an impact!
• A comprehensive, structured HR and professional onboarding process with cross- departmental introductions and feedback sessions.
• Take advantage of our complete Lecturio training platform for free for your personal and professional development.
• Free access to coaching sessions and other mental health benefits.