Head of In Silico Drug Toxicity/VP of Toxicology

Deep Origin

6d•Remote

About The Position

Deep Origin is building an operating system for science that transforms how life science research is conducted. Led by Michael Antonov, co-founder of Oculus, and backed by Formic Ventures, we are redefining the infrastructure behind modern drug discovery. We are now building the next-generation platform for predicting drug toxicity in silico, transforming how pharmaceutical companies evaluate safety before clinical trials. Our mission is to reduce failure rates, accelerate drug development, and eliminate unnecessary animal testing through high-fidelity computational models of human biology. We are not building incremental QSAR tools. We are building foundational infrastructure for predictive toxicology in the age of AI, systems biology, and large-scale computation. We are seeking a Head of In Silico Drug Toxicity to own, define, and scale our computational toxicology platform end-to-end. This role operates as the general manager of the platform — effectively a CEO of the product — with full ownership across scientific vision, technical architecture, product strategy, and execution. You will work cross-functionally with ML/AI teams, computational biologists, toxicologists, engineers, and commercial teams to build a category-defining platform for predictive toxicology. This role requires both deep technical leadership and executive-level strategic thinking, with the ability to translate cutting-edge science into scalable, enterprise-ready systems.

Requirements

15+ years in computational biology, toxicology, drug discovery, or related domain.
Proven experience designing and deploying computational models for toxicity or biological systems.
Demonstrated ability to develop novel modeling approaches beyond industry-standard methods.
Deep hands-on experience designing and deploying computational toxicology models across mechanistic, statistical, and machine learning paradigms.
Demonstrated ability to design innovative modeling approaches, not just apply existing frameworks.
Expertise in integrating ML/AI, systems biology, PK/PD modeling, and real-world data into cohesive predictive systems.
Strong track record evaluating tradeoffs between mechanistic modeling and statistical/ML approaches.
Ability to identify breakthrough opportunities beyond current industry standards.
Experience developing novel model architectures, not just QSAR or legacy approaches.
Comfortable discussing mechanistic toxicity pathways, ML architectures, regulatory strategy, and platform design.
Predictive/computational toxicology.
Systems pharmacology or systems biology.
Mechanistic modeling.
ML/AI in drug discovery.
PK/PD or ADMET modeling.
Strong understanding of preclinical safety workflows.
Familiarity with regulatory frameworks (FDA, EMA, ICH).
Experience working with complex and proprietary pharma datasets.
Awareness of data limitations, bias, and validation challenges.
Experience leading large, interdisciplinary technical teams.
Ability to operate as both a strategic leader and a technical decision-maker.
Executive presence with senior pharma stakeholders.
Strong communication and cross-functional leadership skills.
Experience building platforms, teams, or systems from zero to scale.
Comfortable operating in ambiguity and defining direction.
Strong bias toward action, ownership, and iteration.

Responsibilities

Define and drive the long-term roadmap for in silico toxicity prediction.
Design innovative modeling approaches across mechanistic and ML paradigms.
Integrate ML/AI, systems biology, PK/PD modeling, and real-world data into a unified platform.
Evaluate tradeoffs between mechanistic modeling and statistical learning approaches.
Identify breakthrough opportunities beyond current industry standards.
Translate scientific capabilities into robust, scalable software systems.
Partner closely with engineering to build secure, enterprise-grade infrastructure.
Ensure scientific rigor, reproducibility, and regulatory alignment.
Define product strategy for pharma-facing platform offerings.
Develop novel model architectures beyond standard industry approaches.
Design defensible strategies for acquiring and structuring proprietary datasets.
Build long-term data advantages through strategic partnerships (pharma, government, research).
Establish validation frameworks that balance scientific credibility and real-world applicability.
Engage directly with senior R&D and safety leaders at pharmaceutical companies.
Represent the company in scientific, regulatory, and industry forums.
Shape strategic partnerships and co-development initiatives.
Support business development and fundraising with scientific authority.
Build and lead a world-class interdisciplinary team (ML scientists, computational biologists, toxicologists, engineers).
Drive alignment across science, engineering, product, and commercial teams.
Establish a culture of technical rigor, speed, and ownership.
Mentor technical leaders and build scalable organizational structures.