Computational design of biological experiments for model development

Inceptive is seeking a Computational Design of Biological Experiments for Model Development specialist to contribute to the development of AI-designed drugs. The company focuses on advancing molecular design through large-scale foundation models, which are trained on diverse biological datasets and refined through experimentation and feedback. This role involves working closely with AI researchers and biologists to understand and improve these models. The main day-to-day responsibilities include investigating how model performance is affected by data quantity, quality, and composition. You will develop biologically meaningful evaluations and benchmarks, design and execute experiments to understand model behavior, and identify potential artifacts, bias, and noise in datasets. Additionally, you will work on identifying promising datasets for model training, developing computational pipelines, and collaborating with biologists to translate biological questions into measurable experiments. You will also analyze and communicate experimental findings to inform decisions across teams. To qualify for this role, you must have a PhD in computational biology, statistics, physics, machine learning, or a related quantitative discipline, or equivalent practical experience with a record of publications or open-source tooling. Strong quantitative reasoning and statistical intuition are essential, as is experience analyzing high-throughput sequencing data. Familiarity with AI/machine learning methods, publicly available biological datasets, and proficiency in Python and common scientific computing libraries are required. Excellent communication skills and the ability to work with team members across the US and Europe are also necessary. Nice-to-have skills include 3+ years of post-PhD experience in computational biology, biostatistics, or machine learning research. The role is based in an office environment with a collaborative, antedisciplinary team. The company offers a competitive compensation package, 30 days of paid vacation, comprehensive health insurance, and a learning and development budget. Regular company retreats and wellness benefits are also provided. What the role asks for: - PhD in computational biology, statistics, physics, machine learning, or a related quantitative discipline, or equivalent practical experience, with record of publications or open source tooling in these fields - Strong quantitative reasoning and statistical intuition - Experience analyzing high throughput sequencing data (e.g. RNA-seq, functional genomics / transcriptomics, MPRA), with a focus on robust statistical analysis - Experience collaborating closely with AI/machine learning researchers or applying machine learning or generative AI tools to scientific problems - Familiarity with current AI/machine learning methods, including generative foundation models, representation learning, and model evaluation - Familiarity with publicly available biological datasets and data derived from high throughput assays - Capable programmer in Python and common scientific computing libraries - Excellent written and verbal communication skills, including the ability to explain complex findings to audiences with diverse technical backgrounds - Availability to work with team members across US and Europe, with meetings starting at 8am PT and ending at 7pm CET - Readiness to travel several times a year for company retreats and business events - Nice-to-have: 3+ years of post-PhD experience in computational biology, biostatistics, machine learning research, or a related field