Senior RNA Foundation Models Scientist

Insilico Search Partners; Boston (MA); On-site; USD 180,000 - 240,000; Full time

Job summary

Insilico Search Partners is seeking a Research Scientist, Machine Learning Foundation Models to lead architecture, training, and validation of large-scale models for RNA biology. You will partner with computational biologists and drug developers to ensure models capture biologically meaningful representations.

The role requires a PhD or equivalent, hands-on expertise with CNNs, Transformers, and sequence/state-space models on genomic data, plus strong PyTorch proficiency for training and

Qualifications

• PhD or equivalent with a strong research focus in Computational Biology, ML, CS, or related field.
• Hands-on expertise building foundation models: CNNs, Transformers, sequence/state-space models applied to biological/genomic data.
• Proven track record building foundation models for RNA applications.
• Strong PyTorch proficiency; experience training and debugging large-scale deep learning models.

Responsibilities

• Lead architecture, training, and scientific validation of large-scale foundation models on genomic, transcriptomic, and single-cell data.
• Embed deep biological priors into model architectures and training objectives relevant to RNA biology.
• Collaborate with computational biologists and drug developers to ensure biologically meaningful representations.
• Demonstrate scientific validity on frontier problems in RNA-based genetic medicine.

Skills

Foundation models

CNNs

Transformers

Sequence models

State-space models

PyTorch

Genomic data analysis

Education

PhD in Computational Biology / ML / CS

Tools

PyTorch

Job description

Insilico Search Partners is seeking a Research Scientist, Machine Learning Foundation Models to lead architecture, training, and validation of large-scale models for RNA biology. You will partner with computational biologists and drug developers to ensure models capture biologically meaningful representations.

The role requires a PhD or equivalent, hands-on expertise with CNNs, Transformers, and sequence/state-space models on genomic data, plus strong PyTorch proficiency for training and