G

Genesis Molecular AI Tech Stack

Foundation models for accelerated small-molecule drug discovery

Biotechnology Research Burlingame, California 51–200 employees Privately Held

Genesis Molecular AI runs a proprietary generative AI platform (GEMS) that combines neural networks with physics-based constraints to design and optimize drug molecules. The tech stack—Python, PyTorch, PyTorch Geometric, RDKit, and UniProt—shows deep chemistry-ML integration; they're adopting MCP, likely to expand model capabilities. Hiring skews heavily research (10 roles) with a smaller engineering team (7), suggesting they're prioritizing scientific output and experimental validation over product infrastructure, while data scaling and foundation-model pretraining remain open challenges.

Tech Stack 12 technologies

Core StackPython PyTorch GraphQL PyMOL RDKit PyTorch Lightning PyTorch Geometric Ray UniProt REST cryo-EM

AdoptingMCP

What Genesis Molecular AI Is Building

◆Challenges

Scaling data infrastructure
Novel targets with limited chemical precedents
Accelerating drug discovery
Advancing generative ai for drug discovery
Reducing ml-biology friction
Tackling core challenges in generative modeling
Scaling model pretraining
Optimizing post-training pipelines
Scaling foundation models
Challenging drug discovery programs

▲Active Projects

Build computational chemistry workflows for drug discovery
Productionizing computational methods for molecular property prediction
Small molecule drug discovery programs
Project-specific computational approaches
Transformative research projects in generative modeling for molecular systems
Nucleus platform development
Gems ai system
Scaling data infrastructure for qm and md jobs
High-impact research project on generative ai foundation models
Computational methods research platform

Hiring Activity

Steady20 roles · 8 in 30d

Department

Research

10

Engineering

7

Product

2

Data

1

Seniority

Intern

7

Senior

6

Staff

4

Principal

2

Lead

1

Company intelligence

Find more companies like Genesis Molecular AI by tech stack, pain points and active projects

Get started free

About Genesis Molecular AI

Genesis Molecular AI develops foundation models for molecular discovery, targeting the drug-design bottleneck where traditional chemistry and high-throughput screening are slow and expensive. The company operates a fully integrated lab in San Diego alongside R&D in Burlingame, CA and New York, enabling rapid cycles of AI-generated predictions and wet-lab validation. GEMS, their core platform, combines generative and predictive models—including a diffusion-based model called Pearl—to generate promising small-molecule candidates, optimize leads, and accelerate hit-to-candidate progression. They're building an internal pipeline against high-value targets and have signed platform partnerships with large pharma (Gilead, Incyte), indicating traction beyond their own drug programs.

HeadquartersBurlingame, California

Company Size51–200 employees

Hiring MarketsUnited States, Peru

Frequently Asked Questions

What is Genesis Molecular AI's technology platform?

GEMS (Genesis Exploration of Molecular Space), a proprietary generative and predictive AI system that integrates deep learning with physics-based models to design and optimize small-molecule drugs. Includes Pearl, a diffusion-based model for structure prediction.

What tech stack does Genesis Molecular AI use?

Python, PyTorch, PyTorch Geometric, RDKit, PyMOL, Ray, UniProt, REST, and GraphQL. They're adopting MCP and running cryo-EM workflows for computational chemistry.