AI / ML Engineer

EPM Scientificabout 1 year ago
San Francisco, California, United States
Remote
Full-time
Junior Level (1-3 years)

Job Description

Position Overview

A longevity-focused start-up stealth company is on a mission to create a new "higher" level of human species – one with a drastically longer health span, superior intelligence, and a seamless connection to digital intelligence. As an AI / ML Engineer, you will be part of a dynamic team building software tools to conduct AI analysis of big data. This analysis targets membrane surface proteins in pathological aging and cancer cells, enabling spatial visualization of aging and disease severity.

Key Responsibilities

  • Develop and implement advanced AI analysis pipelines to extract insights from multi-modal data (gene expression, spatial, imaging) for identifying membrane surface proteins.
  • Design, build, and optimize scalable pipelines for high-dimensional genomic, imaging, and molecular datasets.
  • Integrate and visualize data through interactive dashboards for clinicians and researchers.
  • Collaborate closely with data engineering and biology teams to map senescence signatures and uncover potential therapeutic targets.

Required Qualifications

  • Strong background in Machine Learning / Deep Learning Engineering with experience in multi-modal data integration, classification, clustering, anomaly detection, and feature selection.
  • Proficiency in designing and implementing computational models and expertise in model explainability techniques (e.g., SHAP, LIME).
  • Hands-on experience with Python (NumPy, pandas, scikit-learn, PyTorch/TensorFlow), AutoML frameworks, and Hugging Face transformer models.
  • Experience in building scalable data pipelines using tools such as Apache Spark, Dask, AWS/GCP BigQuery, MongoDB, and PostgreSQL.
  • Skilled in developing interactive data visualization tools using frameworks like Plotly Dash, Streamlit, or R Shiny.

Preferred Qualifications

  • Familiarity with AI-based protein/peptide design techniques (e.g., AlphaFold, RFdiffusion, ProtBERT) and bioinformatics workflows.
  • Experience with single-cell RNA-seq (scRNA-seq), spatial transcriptomics analysis, and protein expression pattern analysis.
  • Knowledge of ontologies and databases such as UniProt and the Cell Surface Protein Atlas, along with tools like Scanpy, Seurat, Bioconductor, or Cell Ranger.

Benefits & Perks

  • Stock Options granted at founding-level terms based on skill set and commitment.

Required Skills

Machine Learning
Database Integration (MongoDB, PostgreSQL)
Data Engineering
PyTorch/TensorFlow
Hugging Face models
Python (NumPy, pandas, scikit-learn)
Dask
Distributed Computing
Data Visualization (Plotly Dash, Streamlit, R Shiny)
Deep Learning
Apache Spark
AWS/GCP BigQuery
Big Data Handling
Multimodal Data Integration
AutoML frameworks