About Us

Alta is reinventing how the world sources critical minerals — using protein-based chemistry to extract rare earth elements and other essential materials from challenging feedstocks with unmatched selectivity. By dramatically reducing the cost and environmental impact of mineral separation, Alta is making it possible to unlock new sources of supply for 21st-century technologies. As global demand accelerates, securing these materials has become one of the most urgent challenges facing U.S. competitiveness and national security. Backed by top investors and government partners, Alta is growing fast and hiring mission-driven scientists and engineers to help us scale our platform and transform the future of mining.

How we work

Speed is part of our DNA. We’re building first-of-a-kind technology and facilities, which means the path isn’t always mapped. We’re comfortable with ambiguity: making sound, timely decisions guided by clear priorities, adapting quickly as we learn, and keeping a relentless focus on moving our business forward. We commit to fixed milestones on compressed timelines and hold ourselves accountable without compromising on safety or rigor.

Location: Boulder, CO

Reports To: Sr. Director, Applied Biology

Role Summary

The Head of Computational Biology will be responsible for hands-on technical execution and building and leading a small team. They will integrate Alta’s design-build-test-learn (DBTL) data with in silico and bioinformatics approaches to improve predictions of protein expression, activity, specificity, and manufacturability. A key requirement for this role is a demonstrated ability to translate computational models into experimentally validated candidates that perform in the lab, can be manufactured at scale, and advance toward commercialization, rather than optimizing model performance alone.

The individual will develop and implement computational approaches that connect protein design, experimental results, and predictive modeling to accelerate iterative learning. They will work closely within the Applied Biology group and with LIMS/software developers and Analytical Chemistry groups to define data requirements, experimental workflows, and automation systems that ensure data quality, provenance, and reliability. They will translate research needs into scalable workflows, integrating sample tracking, data capture, analysis, and model feedback.

The ideal candidate combines deep computational expertise with scientific rigor, strong cross-functional communication, and the ability to move between analytical problem-solving, computational development, and team leadership.

Key Responsibilities

Lead a group to develop model classifications and scoring for protein candidates and chemistries using in silico and real-world data sources.
Establish protein and peptide molecular dynamics and quantum mechanics workflows for in silico scoring.
Execute workflows hands-on, personally contributing to model development, code, and analysis alongside the team.
Define success metrics tied to company outcomes (experimentally confirmed hits, manufacturable leads, candidates advanced toward commercialization) rather than model-only benchmarks.
Build pipelines from existing sequence databases and 3D modeling data.
Work with a team to develop and implement model fine-tuning using high-throughput performance data.
Leverage protein manufacturing data to enhance workflows and predict lead-candidates for scalable production.
Deploy generative AI approaches for streamlining workflows.
Collaborate with the data science team to implement genotype-to-phenotype relationship tracking to complete the learn cycle for model refinement.
Work across teams to build out a world-class tracking system for proteins across the design, build, test, and scale workflows.
Leverage sequencing data, production data, and performance tracking to build a state-of-the-art system for multiscale protein and genome engineering.
Partner with the build and test teams to integrate computational workflows, ensuring designs account for real-world constraints such as throughput, cost, and turnaround time.