About VantAI:

VantAI pairs bleeding-edge machine learning techniques with deep systems biology expertise to build computational models that uncover hidden relationships between molecules, targets, and diseases. These models power a best-in-class solution that identifies and generates new molecular entities for targets of interest, repurposes existing molecules at any stage of development, uncovers accurate ADME and toxicological insights, and predicts adverse events likely to influence trial success from deep analysis of systems-based pharmacogenomics. VantAI's in silico platform specializes in modeling complex protein-protein interactions, powering the discovery of biologics and protein degraders in addition to small-molecule drugs. It has helped leading biopharma partners launch new development programs--or revitalize old ones--at a fraction of the time and cost of traditional methods.

About You:

We are looking for talented engineers with an insatiable hunger for solving bleeding-edge scientific problems spanning biology, chemistry, physics, data science and computational science domains to join our core application team.

Successful candidates will develop large-scale scientific workflows, provide support to our scientists on existing workflows and proactively identify areas for increasing automation to reduce inefficiencies. Projects may include developing cheminformatics tools and algorithms; large-scale virtual screening and protein-protein docking; creating scalable on-demand ML inference infrastructure; developing scalable chemical databases; automation of modeling, analysis, and visualization of simulations; and a range of similar tasks integral to achieving our mission of becoming the leading AI-enabled drug discovery in the field of induced proximity.

Our tech stack spans several languages and frameworks, including but not limited to: Python, Go, Rust, React, running in Docker/Kubernetes on GCP. Relevant areas of expertise might include workflow engineering, tool integration, high performance cloud computing, systems engineering, and machine learning, but specific knowledge of any of these areas is less critical than versatility and a willingness to learn and work anywhere in the tech stack. We value individuals who want to make an impact, have a deep intellectual curiosity, enjoy solving challenging problems and have a track record of achievement.

Outcomes for this Role:

• Shaping our product by spearheading new features and services
• Developing software tools to automate or improve processes ranging from data ingestion pipelines to bespoke cheminformatics workflows
• Contributing to the culture of a rapidly growing company
• Being challenged by your colleagues and learning something new every day

Specific Skills and Qualifications:

• Experience working in complex codebases and cloud-native architectures
• Container orchestration and Kubernetes cluster development
• Demonstrated experience creating and managing infrastructure for ML model registry, training, inference and deployment infrastructure
• Strong familiarity with best practices and current state of the art for ML infrastructure
• Experience supporting large-scale model architectures with complex environment requirements
• Data architecture and engineering
• Demonstrated experience with parallel computing and distributed model architectures 
• Ability to break apart existing code; solve ad hoc problems with little help
• Willingness to work with existing codebases
• No task too big or small; strong sense of independence and ownership
• Provide guidance and opinions on implementation/considerations, while having a willingness to compromise 
• Developing/supporting ML models in the cheminformatics, bioinformatics, large language, and/or diffusion model domains (desired)
• Experience working on drug discovery projects (desired)

Salary: $120,000 - $190,000

This band is a reflection of the job description as written. Looking for a higher salary? Apply anyway! We are happy to speak to more experienced candidates who may require a higher salary and discuss that experience in our first touchpoint.