Research Scientist II/Senior, Discovery ML

Iambic Therapeutics, Inc•San Diego, CA

23d•Onsite

About The Position

We are seeking skilled scientists to join our Discovery ML group at Iambic Therapeutics. In this role, you will be a key player in applying advanced ML techniques to support our drug discovery efforts and will be part of drug discovery teams pursuing important therapeutics across multiple indications. The work will include focus on our flagship machine learning models, including Enchant, our multimodal transformer model for predicting drug-target interactions and molecular properties. This role is based at our San Diego headquarters.

Requirements

PhD or equivalent degree in chemistry or another physical science with 3+ years of experience or commensurate degree and job experience. More junior candidates are welcome to apply, title will reflect experience.
Familiarity with using statistical analysis techniques to evaluate, troubleshoot, and adapt models in scientific contexts
Excellent written and verbal communication skills; must be able to articulate complex scientific concepts, technical challenges, and results clearly and concisely to diverse audiences.
Skills: Python programming, statistics, drug discovery

Nice To Haves

PhD or equivalent degree in computational chemistry or machine learning in chemistry
3+ years of experience working in a drug discovery project

Responsibilities

Train, fine-tune, and evaluate machine learning models, assessing how they can best be leveraged in a drug-discovery setting and optimizing their performance
Partner with computational chemists, medicinal chemists and biologists to leverage ML insights for decision-making in high-throughput design-make-test-analyze cycles
Generate value, internally and for partners, from our machine learning models, and collaborate with other discovery teams to shape their use
Communicate results with internal drug discovery teams and machine learning scientists and externally with partners
Support the evolution of our machine learning models by gathering analytical feedback and delivering domain-driven guidance to the machine learning team