About the Company/Team

We are an early-stage startup focused on precision oncology insights to accelerate therapeutic discovery through the integration of structured and unstructured data, AI-assisted knowledge mining, and collaborative scientific insight. We are developing novel tools to identify druggable targets, characterize actionable disease subtypes, and map therapeutic opportunity spaces—beginning with antibody-drug conjugates (ADCs) and combination therapy in oncology. Founder is a physician who has held senior scientific and operational leadership roles at top global biopharma companies, with deep healthcare and startup crossover experiences, and has published extensively.

About the Role

We are seeking a part-time scientific analyst to support content development and signal identification efforts for our product roadmap. This role will focus on the curation, integration, and interpretation of large-scale public datasets and scientific literature, and development of knowledge graph and visualization summaries. The role is ideal for a self-motivated and intellectually curious researcher who enjoys transforming raw biomedical data into clear, actionable insights. Role will collaborate closely with the Founder/Chief Scientific Officer. Responsibilities 1) Oncology ADC Landscape Review and Analysis - Identify and extract relevant content from public datasets and scientific literature (e.g., PubMed, Open Targets, CIViC, DrugBank, ClinicalTrials.gov, PubChem, Thera-SAbDab) 2) Data Curation and Content Development - Normalize and structure data on gene targets, therapeutic agents, trial activity, payload types, and drug development stages - Develop archive and create descriptive summaries of existing knowledge base 3) Model & Graph Development - Development of visual mappings (e.g., knowledge graph, bipartite graph) of omics–disease–therapy relationships - Explore LLM and RAG system applications for insight generation Required Qualifications - Bachelor’s degree plus graduate studies (MS, PhD preferred) in one or more of: Biology, Bioinformatics, Genomics, Systems Biology, Molecular Epidemiology, or Biomedical Data Science - Strong understanding of cancer biology including molecular targets, signaling pathways, and therapeutic modalities - Knowledge of machine learning, LLM/generative AI, or RAG systems - Demonstrated experience working with heterogeneous structured and unstructured biomedical data in a research setting - Proficiency in data cleaning, integration, and literature mining Preferred/Bonus Qualifications - Familiarity with public bioinformatic resources (e.g., Open Targets, TCGA, GTEx, UniProt, COSMIC) - Familiarity with knowledge graph representation and visual storytelling tools - Python/R familiarity a plus Success Traits - Self-starting, organized, and able to work independently while sharing progress regularly - Capable of producing polished, well-sourced summaries, comparative tables, and visualizations - Enjoys working across biology, chemistry, and data science domains to map complex opportunity spaces

We are growing and building out our bench of scientific expertise. There is a possibility of extension and with the candidate playing a more visible role in startup company.