About the Role

We're looking for two Infrastructure Engineers to lead the scaling of our machine learning inference system. You'll be responsible for architecting and maintaining infrastructure that serves 150+ biological ML models, scaling our platform several orders of magnitude to meet rapidly growing demand.

You'll work closely with the founders to design to the constraints of customer needs, unpredictable workloads, and unique Bio-ML models. You'll work with Kubernetes and other tools to orchestrate containerized workloads, optimize resource allocation, and ensure high availability across our model serving infrastructure.

Most importantly, you should thrive in a fast-paced startup environment where you'll wear multiple hats, learn new technologies quickly, and help solve novel technical challenges. We value engineering judgment, problem-solving ability, and the capacity to build systems that can evolve with our growing needs.

Techstack:

• Python, React, AWS (EC2, S3, DynamoDB), Docker, CUDA, Conda, TensorFlow/PyTorch; notebooks; bash/Slurm; APIs & web apps.

Requirements

• Solid programming and automation skills
• Experience with containerization and orchestration concepts
• Cloud platform knowledge (AWS/GCP/Azure)
• Located in the SF Bay Area or able to relocate to the Bay Area
• Onsite expectation: Team currently onsite in SF ~5 days/week.

Preferred

• Experience scaling production systems
• Kubernetes experience
• Infrastructure as code tools (Terraform, Pulumi)
• Monitoring and observability tools
• Experience with GPU workloads

Technology

Our technology sits at the intersection of DevOps, MLOps, and Computational Biology. We deal with problems ranging from scaling ML inference on AWS for hundreds of GPUs to dissecting pdb files with Biopython. We deploy a wide range of open source ML models for customers, navigating between Docker containers, Colab notebooks, bash scripts, slurm jobs, and more.

Our Interview Process

We keep our process focused, transparent, and designed to give both sides a clear sense of fit.

1. Recruiter Screen (15-30 minutes) - Virtual
Meet with our recruiter to dive into your background, interests, and what you're looking for next. We'll also walk you through the company, team, and role.

2. Technical Interview (90 minutes) - Virtual

• Co-Founder Interview (30 minutes): A conversation with Deniz Kavi (CEO & Co-founder) about product, collaboration, and how you approach building in an early-stage environment.
• Technical Deep Dive (60 minutes): A live coding and problem-solving session with Sherry Liu (CTO & Co-founder) or a member of our engineering team.

3. Onsite (1 day) - San Francisco
Spend a day with us working on a mini project and meeting the team.