SkyhawkTx

Skyhawk is committed to discovering, developing and commercializing small molecule therapeutics that correct RNA splicing (e.g. Evrysdi). We work on some of the world’s most intractable diseases including cancer, neurological conditions, and other therapeutic areas/targets previously considered “undruggable.” Skyhawk is looking for a multi-talented Data and DevOps engineer to join our Platform team. In this role, you will work closely with a diverse team of world-class scientists and engineers. You will help us accelerate Skyhawk’s novel drug discovery and development platform, SkySTAR. Your primary responsibilities will be to design, implement, deploy, and maintain data-processing and -modeling toolbox that powers collaborative interactions between scientists on our platform and makes optimal use of our rich in-house data. This is a key technical role providing many opportunities for significant impact and growth. You will learn from a cross-functional team of experts in Machine Learning, Bioinformatics, Genomics, Structural Biology, Chemistry, and Drug Discovery. You will manage unique scientific data, help grow Skyhawk’s collaborative data science culture, and ultimately enable better health for our patients! Primary Responsibilities: • Design, implement, and maintain ETL workflows from multiple internal & external data sources • Deploy and maintain a data warehouse that cleans and fuses data for our cloud ML workflows • Utilize cloud APIs to support the prototyping, training, and deployment of predictive models • Continuously deploy predictive models and insights curated from them to interactive dashboards • Record usage analytics and gather expert feedback on predictors to improve our ML workflows • Establish robust CI/CD practices for our code, data, and results to minimize technical debt • Collaborate widely across the entire R&D team to codify their insights and meet their use cases • Manage project timelines and schedules of projects with internal personnel and external vendors Education/Skills/Experience: • BS/MS in a technical field or related background with at least 3 years of practical experience (preferred: Computer Science, Applied Math/Statistics, Physics, Chem/Bio Engineering) • Expertise in one or more general-purpose programming languages (we use: Python, R, Perl, Julia) • Demonstrated ability to write production code (readable, maintainable, tested, and documented) • Demonstrated experience in building cloud-based data infrastructure (we use: GCP and AWS) • Experience with wrapping & deploying models from ML frameworks (we mainly use: Keras and TensorFlow) • Familiarity with user-facing web services and applications (we use: Spotfire, Jupyter, R/Shiny, Dash) • Proficiency in Linux (including shell scripting), experience with database languages (SQL or No-SQL) and experience with code/data/workflow version control practices and tools (we use: git/dvc/cml) • Experience with biochemical and genomic data is a plus (we use: RNA sequences, chemoinformatics) • Ability to manage multiple projects simultaneously and manage priorities flexibly. • Excellent written and verbal communication skills; organizational and documentation skills. • Relaxed and fun attitude that helps good culture building. Passion for improving people’s health! More info and application instructions at: https://skyhawktx.page.link/platform_engineer