EPM Scientific
Founding Machine Learning Scientist - mRNA (San Francisco County)
EPM Scientific, San Francisco, California, United States, 94133
Founding Machine Learning Scientist - mRNA
About Our Client Backed by top-tier investors and led by researchers from world-class AI-for Biology labs with deep expertise in large-scale biological modeling, our client is building AI foundation models to transform RNA-based therapeutics. They are pioneering a new approach to mRNA design and optimization. They are seeking a Founding Machine Learning Research Scientist to join their early-stage team. This is a hands-on role for someone excited to build from the ground up. This scientist will be driving strategy, shaping core models, infrastructure, and culture at a company defining the future of RNA therapeutics.
Responsibilities Design, train, and optimize foundation models for mRNA sequence and structure modeling. Develop novel deep learning architectures, including transformer-based models tailored to RNA data. Build scalable pipelines for large-scale training and inference across diverse RNA datasets. Collaborate with computational biologists to ensure models produce interpretable, biologically meaningful outputs. Translate open-ended biological questions into rigorous computational experiments. Provide technical leadership and mentorship as the team grows.
Qualifications Experience in machine learning, deep learning, and large-scale data analysis (academic or industry). Bachelor's degree or higher in Computer Science, Machine Learning, Computational Biology, or related field. Strong proficiency in Python and deep learning frameworks (PyTorch preferred). Proven experience building and optimizing large-scale models, ideally for sequence or structural data. Demonstrated ability to take projects from concept to production or publication.
Preferred Ph.D. with a strong publication record in top ML or computational biology venues. Experience with RNA biology or related omics data (RNA-seq, MPRA, structure probing). Familiarity with generative modeling, multi-modal architectures, or diffusion models. Startup or fast-paced environment experience; proactive and comfortable with ambiguity.
About Our Client Backed by top-tier investors and led by researchers from world-class AI-for Biology labs with deep expertise in large-scale biological modeling, our client is building AI foundation models to transform RNA-based therapeutics. They are pioneering a new approach to mRNA design and optimization. They are seeking a Founding Machine Learning Research Scientist to join their early-stage team. This is a hands-on role for someone excited to build from the ground up. This scientist will be driving strategy, shaping core models, infrastructure, and culture at a company defining the future of RNA therapeutics.
Responsibilities Design, train, and optimize foundation models for mRNA sequence and structure modeling. Develop novel deep learning architectures, including transformer-based models tailored to RNA data. Build scalable pipelines for large-scale training and inference across diverse RNA datasets. Collaborate with computational biologists to ensure models produce interpretable, biologically meaningful outputs. Translate open-ended biological questions into rigorous computational experiments. Provide technical leadership and mentorship as the team grows.
Qualifications Experience in machine learning, deep learning, and large-scale data analysis (academic or industry). Bachelor's degree or higher in Computer Science, Machine Learning, Computational Biology, or related field. Strong proficiency in Python and deep learning frameworks (PyTorch preferred). Proven experience building and optimizing large-scale models, ideally for sequence or structural data. Demonstrated ability to take projects from concept to production or publication.
Preferred Ph.D. with a strong publication record in top ML or computational biology venues. Experience with RNA biology or related omics data (RNA-seq, MPRA, structure probing). Familiarity with generative modeling, multi-modal architectures, or diffusion models. Startup or fast-paced environment experience; proactive and comfortable with ambiguity.