Machine Learning Software Engineer
Harrison Clarke Groupoperates at the intersection ofSearch, Venture and Media. Since 2017, the Group has helped Founders and Investors build talent-dense companies through Harrison Clarke(Startup Search), ARKE(Mission-Critical Workforce Solutions), Harrison Clarke Ventures(Venture Capital) and Inside the Silicon Mind(Founder and Investor Media Platform).Harrison Clarke (Startup Search) is your working exclusively with a well-funded, Tier 1 VC-backed startup that is building a connected model of entire drug development programs. Instead of leaving critical knowledge scattered across documents, slide decks, people, and institutional memory, our client are creating a living, structured representation of the full R&D process, from discovery through development. Their goal is to give scientists, program teams, and decision-makers a coherent, queryable, and continuously updated view of complex drug programs so they can move faster, reduce risk, and make better decisions.
About the Role:
As a Machine Learning Software Engineer, you will design, build, and productionize the core ML systems that power this connected model of drug development. You will work on problems involving structured and unstructured data, knowledge representation, model training and evaluation, and the reliable delivery of ML capabilities into real scientific and operational workflows. This is a hands-on role with significant ownership. You will help define how machine learning is applied to one of the most complex and high-stakes domains in the industry.
What You’ll Do:
Design and implement machine learning systems that extract, structure, and connect knowledge across the drug development lifecycle.
Build robust data and model pipelines that turn heterogeneous sources (documents, experimental data, structured records, expert input) into reliable, usable representations.
Develop and iterate on models for information extraction, relationship modeling, reasoning over program knowledge, and downstream decision support.
Own the full lifecycle of ML features, from research and prototyping through production deployment, monitoring, and continuous improvement.
Collaborate closely with domain experts, product, and other engineers to ensure models are accurate, interpretable, and genuinely useful to scientific and program teams.
What We’re Looking For:
Strong software engineering fundamentals with several years of experience building production systems.
Hands-on experience developing and deploying machine learning models in real products or internal platforms.
Comfort working with both structured and unstructured data, and experience building data/ML pipelines.
Solid understanding of modern ML techniques and practical trade-offs (accuracy, latency, maintainability, explainability).Experience with Python and common ML/data tooling (e.g., PyTorch, scikit-learn, Spark, modern data/ML platforms).Ability to take ambiguous, high-context problems and drive them to clear technical solutions.
Nice to Have:
Experience with knowledge graphs, information extraction, retrieval systems, or LLM-based applications. Background in biotech, pharma, computational biology, or other scientific domains.