Pay: $60-$65/hr
REQUIRED:
MS degree with 5+ years of experience or PhD with 0+ years of experience in a quantitative field such as Bioinformatics, Computational Genetics, Biostatistics
- Strong Python-based ML experience
- PyTorch
- TensorFlow
- Scikit-learn
- predictive modeling
- deep learning
- Experience actually building/training models
- not just running pipelines
- Bioinformatics or omics exposure
- RNA-seq
- genomics
- CRISPR
- multi-omics
- GWAS
- single-cell
- HPC/cloud computing experience
The successful candidate will work closely with stakeholders in the Quantitative Insights Lab (QuIL) organization to support cross-project data science efforts spanning in silico perturbation analysis, toxicogenomics, and mechanistic profiling. This work will contribute to the development and evaluation of predictive and comparative frameworks that help rank drug targets, drug combinations, and biological signatures across multiple experimental systems. This will include integrating large-scale omics data to support combination strategy assessment across indications.
Key Responsibilities
• Support perturbation analyses to rank promising drug targets and drug combinations for efficacy prediction.
• Contribute to the development of combination signature estimation approaches and ranking frameworks.
• Ingest, clean, and preprocess multi-modal datasets to enable downstream analysis and modeling.
• Apply AI/ML methods where appropriate, including the use of large language models to accelerate analysis, coding, and workflow development.
• Demonstrate understanding of model development principles, including training, testing, and cross-validation, and help select appropriate models for specific problem types.
• Collaborate with scientific and technical teams to translate biological questions into computational solutions, execute and troubleshoot analyses, and communicate findings clearly and reproducibly.
Required Technical Skills
1. Experience processing and analyzing RNA-seq, imaging data, CRISPR screens, or other similar NGS/genomic data.
2. Proficient in statistical and programming languages such as R and Python, with ability to perform parallel computing using HPC
3. Experience writing custom functions in R or Python to statistically interrogate and visualize omics data.
4. Demonstrated ability to execute custom computational analysis plans leveraging Client algorithms, relevant databases, and AI/ML approaches where appropriate.
5. Familiarity with machine learning fundamentals, including model selection, training, testing, and cross-validation.
6. Experience using LLM-based tools or coding assistants to support analysis, coding, and workflow development.
#LI-MF1