Careers

 

Help us invent the future of pharmaceutical research.

Atomwise uses artificial intelligence to help discover new medicines. Based in San Francisco and funded by Data Collective, DFJ, and Khosla Ventures, we created the first Deep Learning Neural Network for drug discovery and design – AtomNet.

Over the last 2 years, AtomNet has been deployed to help invent new potential medicines for 27 disease targets. We work with leading research groups at top organizations including Harvard University, Stanford University, Scripps Research Institute, and several large pharmaceutical companies, advancing the frontiers of human health.

Atomwise’s notable successes have included promising compounds for the treatment of multiple sclerosis, Ebola, and botulinum neurotoxin, as well as work in cancer, malaria, and metabolic diseases. Today, Atomwise searches 1 million potential drug molecules every 24 hours.

Now, we are actively seeking new team members to help us do great science and make big discoveries. That’s where you come in.

We invite you to read more about Atomwise on arXiv, BBC, Vice, NPR, The Wall Street Journal, and TechCrunch.

We are not currently offering visa sponsorships for these positions, please only apply if eligible to work in the U.S.

 

  • Senior Infrastructure Engineer

  • Senior Data Engineer

  • Computational Chemist

Senior Infrastructure Engineer

We are looking for a senior engineer to scale up both our production infrastructure and internal R&D pipeline. You will build a robust, flexible, and extensible computing and storage platform; this platform is going to support the next level of machine learning innovation and execution of our growing number and extent of our research partnerships.

You will:

  • Work with the entire team to understand and analyze the current state of the system, identify pain points and design possible solutions
  • Estimate engineering effort, identify dependencies, plan and roll out implementations
  • Design local and cloud-based storage to support our internal R&D and production projects
  • Streamline and automate our data generation and processing pipeline
  • Build an automated production workflow for cheminformatics scientists
  • Create a consistent process to synchronize data between local and cloud-based environments, including backup and recovery schemes

Required Qualifications:

  • Bachelors or Masters degree in computer science or related discipline, with at least 5 years of professional experience
  • At least 5 years of programming experience in Python, Perl, Bash, or related scripting languages
  • Proficient in cloud computing environments (AWS/Azure/GCE)
  • Experience in designing and scaling storage environments
  • Solid computer science fundamentals in data structures, algorithm design, and complexity analysis
  • Proficiency in systems software concepts (file systems, memory management, distributed systems, networking, etc)

Preferred Qualifications:

  • In-depth knowledge of relational databases, NoSQL and distributed systems
  • Deep understanding of Linux filesystems
  • Experience as system administrator or devops
  • Experience in working with chemical or biological data
  • Exposure to machine learning tools and frameworks

 

  • Apply to this job

Senior Data Scientist

Our success critically depends on the validity, accuracy, completeness and consistency of our chemical and biological data sets; they are the foundation of all our systems and machine learning models. Therefore, we are looking for a senior engineer to take ownership of our entire data curation and processing pipeline.

You will:

  • Work with the entire team to understand and analyze our current data processes
  • (Re)design and improve our process of acquiring, cleaning, transforming, and storing data
  • Analyze data for coverage/redundancies/accuracy/reliability — how well are we covering the chemical and proteome spaces, where should we focus on getting more data
  • Implement algorithms for data cleansing and confidence — identify possible curation errors and curation inconsistency across different data sources
  • Design, build, and maintain benchmark data sets
  • Work with the production engineer to automate our benchmark suite

Required Qualifications:

  • Bachelors or Masters degree in computer science or related discipline, with at least 5 years of professional experience
  • At least 5 years of programming experience in Python, Perl, Bash, or related scripting languages
  • Experience applying Cheminformatics tools to analyze chemical or biological datasets
  • Deep familiarity with Linux command-line environment
  • Experience with statistical analysis and data visualization (Python/R)

Preferred Qualifications:

  • In-depth knowledge of relational databases, NoSQL and distributed systems
  • Experience working with scalable algorithms utilizing large amounts of data
  • Knowledge of machine learning concepts and techniques
  • Experience with cloud computing environments (AWS/Azure/GCE)
  • Experience working with terrible gorpy real world data, entered by hand by non-computer scientists
  • This makes you either nod sadly or shake your head (also sadly): http://www.bbc.com/news/technology-37176926

 

  • Apply to this job

Computational Chemist

We are looking for a computational chemist to join our production team. The production team is in charge of identifying customer needs, implementing the most suitable solution, executing projects using Atomwise technologies, and communicating results.Our customers are scientists; you should be, too. Results should be considered guilty until proven innocent: sanity checking, skepticism, problem solving, analysis, and investigation are our constant companions. You should be comfortable discussing and reasoning about projects with the precision necessary to deliver what the customer needs, and possess enough clear articulable pragmatism to get things done even in the face of inevitable and unavoidable ambiguity.

You will:

  • Interact with customers to understand their project requirements
  • Generate and analyze predictive results, and deliver these to our clients
  • Communicate our results and capabilities through scientific publications
  • Analyze, curate, and automate processing of our biochemical databases
  • Help develop our modeling software

Required Qualifications:

  • M.Sc in computer science, chemistry, statistics, math, physics, or a related field. Ph.D preferred
  • +3 years experience in computational chemistry or cheminformatics
  • Experience in molecular modeling (structure or ligand based, e.g., pharmacophore modeling, QSAR, docking, MD simulations, etc.)
  • Comfortable on the Linux command-line
  • Undergraduate knowledge of statistics
  • Undergraduate knowledge of chemistry/biochemistry/biology

Preferred Qualifications:

  • Good knowledge in Python, Perl, Bash, or related scripting languages
  • Statistical modeling
  • Experience with cloud computing environments (AWS/Azure/GCE)

 

  • Apply to this job