Senior/Staff Machine Learning Bioinformatics Scientist

Protillion Biosciences•Carlsbad, CA

About The Position

We are seeking a highly motivated and experienced computational scientist to join our dynamic team in Carlsbad, CA. The successful candidate will lead innovative projects leveraging Bayesian optimization and active machine learning at the intersection of protein design, high-throughput experimentation, and experimental data analysis, contributing to groundbreaking advancements in biotechnology. This role requires a unique combination of technical expertise, strategic thinking, and collaboration with multidisciplinary teams.

Requirements

PhD in Computational Biology, Bioinformatics, Biophysics, Computer Science, or a related field with at least 5 years of relevant industry or postdoctoral experience
Proven expertise in Python programming, with a strong track record of developing scalable and efficient bioinformatics pipelines
Demonstrated experience in designing, training, and applying large language models to solve biological challenges, particularly in protein design
Familiarity with active learning, reinforcement learning, Bayesian optimization, or other iterative learning paradigms in scientific contexts
Deep knowledge of sequencing technologies (Illumina, Oxford Nanopore, PacBio) and analysis methodologies
Exceptional problem-solving skills and the ability to translate complex biological problems into computational solutions
Excellent communication and collaboration skills, with a proven ability to work effectively within interdisciplinary teams

Nice To Haves

Experience with cloud computing platforms (AWS, GCP, or Azure) and containerization technologies (Docker, Apptainer)
Proficiency in machine learning frameworks such as TensorFlow or PyTorch
Knowledge of structural bioinformatics and protein modeling tools
Familiarity with laboratory techniques and experimental validation processes

Responsibilities

Develop and deploy scalable bioinformatics solutions to address complex biological questions
Implement and drive iterative learning cycles between computational bioinformatics and experimental workflows, such as active learning and Bayesian optimization
Design and train multi-objective therapeutic protein design and optimization models using large language models (LLMs) and multi-scale modeling, leveraging our unique capabilities to generate quantitative protein-protein interaction measurements at unprecedented scale
Collaborate closely with experimental scientists to refine models and validate predictions through laboratory experiments
Analyze sequencing data from a variety of platforms, including Illumina, Oxford Nanopore, and PacBio, to extract meaningful insights
Champion a high-quality, scalable code base by adhering to best practices in software development, including unit testing and continuous integration/continuous deployment (CI/CD)
Mentor junior scientists and contribute to fostering a culture of innovation and excellence within the team