Senior Staff Bioinformatics Scientist (AI-guided protein engineering)

Why us

Illumina is the global leader in Next Generation Sequencing (NGS) technology. Through relentless innovation, Illumina has reduced the cost of sequencing a human genome from hundreds of thousands of dollars to below $200. The drastic cost reduction has moved NGS from the laboratory to the clinic, with wide-ranging impact from cancer diagnostics to genetic testing. We invite you to join us in our effort to improve human health by unlocking the power of the genome.

Position summary

We are seeking a Senior Staff Scientist to help build computational tools and data foundation for our protein engineering group across global enzyme engineering programs. This role will connect data structures for high-throughput and mid-throughput screening, participate in method development and evaluation, and help establish semi-closed-loop and closed-loop design-build-test-learn workflows.

The successful candidate will provide senior technical leadership at the interface of protein engineering, AI/ML design, screening data systems, automation, and experimental execution. This scientist will define how screening results become reusable data assets as well as how computational methods are benchmarked and adopted.

The role is based in Singapore. This is an exciting opportunity to be a part of Illumina’s continued growth.

Responsibilities include, but are not limited to:

• Build reusable data foundations for protein engineering. Define data structures, metadata standards, variant lineage, assay context, controls, replicate handling, uncertainty, and negative data capture across high- and mid-throughput screening workflows.

• Enable model-guided enzyme engineering. Develop and evaluate computational workflows that connect sequence, structure, assay, and screening datasets to AI/ML models, design rationale, variant prioritization, and next-round library design.

• Benchmark computational and AI methods. Assess internal pipelines, open-source methods, commercial protein design platforms, and emerging scientific agents using retrospective and prospective performance metrics relevant to enzyme engineering programs.

• Deliver practical tools for project teams. Create reusable scripts, templates, dashboards, lightweight applications, and analysis pipelines that help experimental and computational teams run routine analyses and interpret recommendations efficiently.

• Advance closed-loop DBTL workflows. Help establish semi-closed-loop and closed-loop design-build-test-learn systems in which experimental results are captured, analyzed, modeled, reviewed, and converted into actionable design recommendations.

• Partner across global engineering programs. Work closely with experimental scientists, automation teams, informatics, software engineering, data engineering, chemists, biophysicists, and platform teams to ensure computational workflows align with assay throughput, operational constraints, and program goals.

All listed tasks and responsibilities are deemed as essential functions to this position; however, business conditions may require reasonable accommodations for additional task and responsibilities.

Education, Experience & Attributes required:

• Ph.D. in computational chemistry, computational biology, bioinformatics, computer science or related fields, or equivalent work & educational experience.

• Significant experience leading computational biology, protein engineering, AI/ML, screening analytics, or scientific data infrastructure efforts

• Deep experience applying computational or data-driven methods to protein engineering, enzyme engineering, directed evolution, assay analysis, or related biological design problems.

• Demonstrated ability to design data structures or analytical systems that support reproducible analysis, model training, and cross-project learning.

• Wet-lab experience in high-throughput or mid-throughput screening and/or biochemical assay designs.

• Solid programming skills in at least one of the major programming languages (e.g., C/C++, Python, R).

• In-depth knowledge of protein sequence or structure modelling, protein-ligand interaction predictions and/or molecular simulations.

• Understanding of AI/ML methods and practical experience in adopting AI/ML-driven protein-design models.

• Strong fundamentals in statistical modelling, algorithm design, data analysis, and/or visualization methods.

• Excellent verbal and written communication skills.

• Collaborative, open and self-aware, team player, and able to rapidly integrate into cross functional teams.

• Highly motivated individual with proven ability in thinking innovatively and the proven track record of productive research and development.

• Strong applicants with lesser experience will be considered for a position commensurate with the experience.

Preferred experiences and attributes

• Experience with foundational AI/ML models and protein language models for protein engineering, including generative protein design, zero-shot variant scoring, supervised learning, model-guided library design, denoising and uncertainty-aware learning, and multi-parameter optimization of protein properties

• Experience with structure prediction, protein-ligand or enzyme-substrate modeling, molecular dynamics, docking, or biophysical analysis (e.g. Protein MPNN, RFdiffusion, Boltz, Alphafold)

• Experience developing data standards, assay schemas, dashboards, or lightweight tools for experimental scientists.

• Experience with developing AI agents and agentic workflows for method and application development, and automatic execution and optimization of computational pipelines,

• Deep learning frameworks such as PyTorch, TensorFlow, or JAX

• Large-scale biological data analysis using cloud or high-performance computing environments

• Practical experience with AI/ML model development for protein design.

• Experience with experiments within protein engineering, e.g. directed-evolution, high-throughput screening.

• Experience in using one or more commonly used molecular modelling software, e.g. Rosetta.

• Knowledge of best software development practices and code version control, e.g. Git.

• Knowledge of UNIX environment and shell scripting.

• Experience with high-performance computing, job schedulers, and/or GPU computing.

• Broad knowledge of bioinformatics, genomics, and/or proteomics database, tools, and/or algorithms.

• Knowledge of biochemistry, enzymology, and/or molecular biology.

• Familiarity with next generation sequencing technologies, tools, and/or workflows.