AI / ML Engineer
A longevity-focused start-up stealth company is aiming to create a new "higher" level of human species - one capable of a drastically longer health span, superior intelligence, and seamless connection to digital intelligence. We believe this is the most important event in human history over the last 10 million years. The leap to this new level of humanity will be greater than the evolutionary jump from apes to hominids.
Job Description
This team is building a new software tool that conducts AI analysis of big data to find membrane surface proteins of pathological aging and cancer cells and enables spatial visualization regarding the degree of aging and cancer. The team already has raw single-cell RNA sequencing data for various organs and chronic diseases, and the cells are labeled as p16⁺ (senescent marker positive) or p16⁻ (negative), with gene expression profiles that include both identity markers and disease-related genes. This allows us to compare cell-type-specific expression patterns between senescent and non-senescent cells across different organs and disease states, enabling mapping of senescence signatures and discovery of potential therapeutic targets.
Skill Criteria
Machine Learning / Deep Learning Engineering (Core) Welcoming strong AI/ML candidates even without biology background.
Skills:
- Multi-modal data integration (e.g., gene expression + spatial + imaging)
- Classification, clustering, and anomaly detection of cell states
- Feature selection for biomarker identification
- Model explainability (e.g., SHAP, LIME)
- Ability to design and implement advanced mathematical/computational models inspired by publications such as: A generative statistical model for molecular data' - Nature Methods, 2025 https://www.nature.com/articles/s41592-025-02772-6?t=txA9bviw7ZgRpCBB8SBljA&s=31
Tools:
- Python (NumPy, pandas, scikit-learn, PyTorch/TensorFlow)
- AutoML frameworks
- Hugging Face for transformer models (e.g., BioBERT, ProtBERT)
Data Engineering & Big Data Handling (Core)
Skills:
- Scalable pipelines for high-dimensional genomic, imaging, and molecular datasets
- Database integration across heterogeneous sources (omics + clinical + imaging)
- Distributed computing for large-scale AI training
Tools:
- Apache Spark, Dask, AWS/GCP BigQuery
- MongoDB, PostgreSQL
Data Visualization / Frontend Integration
Skills:
- Developing interactive dashboards for clinicians/researchers
- Visualizing disease or aging severity at cellular/tissue level
Tools:
- Plotly Dash, Streamlit, R Shiny
- Optional) React + D3
Bonus / Preferred Skills
(Not mandatory, but highly desirable for candidates interested in AI + Biology)
- AI-based protein/peptide design (e.g., AlphaFold, RFdiffusion, ProtBERT)
- AI tool development for biology applications (e.g., molecular modeling, drug discovery
Bioinformatics workflows:
- Single-cell RNA-seq (scRNA-seq) and spatial transcriptomics analysis
- Protein expression pattern analysis (e.g., membrane protein localization)
- Familiarity with ontologies & databases (e.g., UniProt, Cell Surface Protein Atlas)
Tools: Scanpy, Seurat, Bioconductor, Cell Ranger
Stock options will be granted at founding-level terms, depending on the skillset and commitment of the candidate.
