Scientist I, Computation Protein Design

Alta Resource Technologies•Boulder, CO

4d•Onsite

About The Position

About Alta Alta Resource Technologies (Alta) is a next generation mining company that uses synthetic biology to separate critical minerals from conventional and unconventional resources, including e-waste. Founded in 2023, the company is expanding its team in Boulder, CO. The exponential growth of new tech industries, as well as the information technology sector, are driving historic growth in mineral demand and stressing existing supply streams. Meeting new demand, diversifying the supply chain, and producing minerals in a more sustainable manner requires the rapid development, deployment and scaling of new technologies. This mineral challenge represents a historic opportunity for technology development and value creation. Alta is proud to be at the vanguard of this mega trend. About the Role: We are seeking a highly skilled Scientist I, Computation Protein Design to join our team and drive innovation in protein design and engineering through good data practices, robust analytical methods and machine learning. This role focuses on leveraging and optimizing foundational AI models to accelerate our protein engineering pipeline. The ideal candidate will have deep expertise in model fine-tuning, evaluation, and selection, with strong data engineering capabilities to support cutting-edge computational biology research.

Requirements

Ph.D. in Computational Biology, Bioinformatics, Computer Science with 1-3 years of relevant industry or post-doctoral experience, or M.S. with 6+ years of relevant industry experience
Hands-on experience with protein foundation models such as ESM-2, ESM-3, ProteinMPNN, RFdiffusion, AlphaFold, or similar architectures
Knowledge of protein design software and molecular modeling tools (Rosetta, PyMOL, Chimera)
Demonstrated experience fine-tuning and working with large-scale machine learning models, preferably protein or biological sequence models
Strong proficiency in Python and modern ML frameworks (PyTorch, TensorFlow, JAX)
Experience with model evaluation methodologies, including cross-validation, performance metrics, and statistical analysis
Solid understanding of protein structure, function, and the principles of protein engineering
Experience with high-performance computing environments and GPU-accelerated computing
Strong communication skills and ability to work collaboratively in interdisciplinary teams
US Citizenship required.

Nice To Haves

Experience with workflow management tools (Nextflow, Snakemake, or similar)
Familiarity with cloud computing platforms (AWS, GCP, Azure) and containerization (Docker, Singularity)
Experience with distributed computing frameworks (Dask, Ray, Spark)
Track record of publications or contributions to open-source projects in computational biology or machine learning

Responsibilities

Fine-tune, adapt, and use foundational protein models (e.g., BoltzGen, ESM, OpenFold derivatives) for protein engineering applications
Develop and implement rigorous evaluation frameworks to assess model performance, including metrics for protein structure prediction, sequence optimization, and functional property prediction
Conduct comprehensive benchmarking studies to identify and recommend the most suitable foundational models for various protein engineering tasks
Design and execute computational experiments to validate model predictions against experimental data
Leverage multiple information sources (including bioinformatic, structural, simulations, and experimental performance data) to improve internal models and develop agentic frameworks
Collaborate with the Applied Biology team to translate models into actionable insights.
Create technical documentation including model assumptions, equations, validation results, and recommendations.
Provide technical mentorship and review for junior engineers and scientists.
Clearly communicate technical findings, risks and recommendations to leadership and project stakeholders.
Contribute to developing data management systems that meet FAIR principles.
Develop analysis code to support the team in analyzing experimental data.
Engineer data into vectorized format for MCP integration
Utilize experimental data to validate and improve model development.