PACT Pharma is an exciting new company in the San Francisco Bay Area. PACT is developing personalized adoptive T cell therapies for the eradication of solid tumors. The identification of neo-epitopes that serve as private mutations for each patient’s cancer creates a unique opportunity to engineer autologous T cells that target and kill tumors expressing these neo-antigens. PACT utilizes technology licensed from the laboratories of Drs. Heath and Baltimore (Caltech) to identify T cells that recognize the neo-epitope. The unique T-cell receptor (TCR) sequences obtained from these neoepitope-reactive cells are then engineered into T cells from the patient’s own blood to produce PACT’s therapeutic product: a tsunami of fresh, active T cells that, following infusion into the patient, recognize and attack each patient’s cancer cells.
We are located in the San Francisco bay area, in the heart of the world’s premier biotechnology research hub. PACT Pharma offers a competitive compensation and benefits package, including aggressive participation in the growth of the company in the form of stock option grants. PACT Pharma is an ambitious cutting-edge undertaking - we fully anticipate our company to become the world’s leader in personalized adoptive T cell therapies for cancer and therefore key to the future of cancer treatment. Currently located in Hayward, CA but will be moving to another location by year end.
Bioinformatics Scientist/Computational Biologist/Data analyst
The ideal candidate should be experienced in the latest machine learning techniques for the development of novel models for drug target discovery from next generation sequencing (NGS) data. The candidate should enjoy operating in an exceptionally dynamic and cooperative environment and will communicate results to and coordinate efforts with a larger cross-disciplinary team of immunologists, biologists, engineers and bioinformaticians.
Working in bioinformatics group and collaborating with biologists with a primary focus on machine learning and cloud computing:
- The candidate is responsible for the development of automated cloud-based NGS pipelines as well as machine-learning models for the analysis of large patient datasets from both internal and public datasets, such as TCGA, GTEx and IEDB.
- She/he will be performing NGS data analysis for variant/neoantigen identification/prioritization and TCR sequence analysis.
- The ideal candidate will hold a Master's Degree or PhD in Bioinformatics, Computer Science, Statistics, Genomic Sciences, Molecular Biology, Genetics, or a related field with 2+ years of hand-on experience in machine learning, and/or bioinformatics software development and research.
- The candidate should have experience in NGS data analysis, including algorithm development.
- The candidate should be experienced in developing deep-learning models using public DL frameworks, such as TensorFlow, Keras, Theano, Caffe, Neon, or pyTorch.
- Strong background of Linux system software development and programming proficiency in R, Python, Perl and/or Java.
An incumbent with experience in the following areas is a plus:
- Developing pipeline with GATK best practice;
- Feature selection and machine learning with proteomics data and sequence characteristics;
- Knowledge of key biological processes, and cancer biology is preferred.