Machine Learning Engineer

About Blank Bio

Blank Bio is a YC-backed TechBio startup building the next generation of RNA foundation models. Our mission is to decode RNA biology to accelerate the discovery and development of RNA-based therapeutics, biomarkers, and diagnostics. We believe RNA is the programmable layer of biology and that advances in AI will unlock its full potential for medicine.

We’re a technical team of PhDs and operators with experience at pioneering TechBio companies (Valence, Recursion, Deep Genomics) and top AI labs. We’re backed by investors like Nova Threshold, Leonis Capital, SignalFire, Define Ventures, and others.

The Role

We are looking for a Machine Learning Engineer to join our founding team. You will be responsible for scaling our models, building the training infrastructure, and ensuring reproducibility across large-scale biological datasets. You’ll work closely with research scientists and biologists to turn cutting-edge machine learning into practical, high-impact tools for RNA biology.

As an early-stage startup, we move fast, work across disciplines, and embrace ambiguity. We’re looking for people who thrive in dynamic environments, are eager to take ownership, and want to help define both the science and the culture of a company at the beginning of its journey.

Responsibilities

• Develop and optimize large-scale ML training pipelines for RNA foundation models.
• Implement distributed training systems (multi-GPU/TPU) and optimize performance at scale.
• Build infrastructure for dataset management, preprocessing, and benchmarking.
• Collaborate with scientists to translate biological questions into ML tasks.
• Contribute to the design and evaluation of new architectures, embeddings, and fine-tuning strategies.
• Maintain high-quality engineering standards, including reproducibility, testing, and deployment readiness.

Qualifications

Must-haves

• 3+ years of work experience
• Proficiency in Python and modern deep learning frameworks (PyTorch, JAX, or TensorFlow).
• Hands-on experience training large-scale models (transformers, diffusion, or sequence models).
• Strong background in distributed training, optimization, and performance profiling.
• Track record of building ML systems that scale and ship.

Nice-to-haves

• Experience with biological or messy, real-world scientific data.
• Background in computational biology, bioinformatics, or adjacent fields.
• Experience in early-stage startups or interdisciplinary ML-for-science projects.

Compensation & Benefits

• Competitive salary and meaningful early-stage equity.
• Comprehensive health, dental, and vision coverage.
• Generous vacation and parental leave policies.