BIOINFORMATICS PROGR 3

Job Function Summary:

Involves developing and utilizing computational tools and systems to analyze and interpret biological or other research data. Utilizes and develops algorithms, computational techniques, and statistical methodologies. Helps in the design of new experiments. Implements end-user needs in database searching and integration. Assists with maintaining the computational infrastructure, local databases, and tracks the flow of samples and information for large-scale studies. Develops analysis tools for use by lab personnel and for public dissemination.

Custom Scope:

Uses skills as a seasoned, experienced bioinformatics programming professional with a broad understanding of computational algorithms and systems; identifies and resolves a wide range of issues / software bugs. Demonstrates good judgment in selecting methods and techniques for obtaining solutions. Operates independently. Demonstrates proficiency with modern AI coding frameworks, for example, Claude, Codex, Cursor, etc., as well as traditional SQL and Python coding. Demonstrates proficiency with modern machine learning toolkits and approaches for classification tasks using large scale datasets, including transcriptomics, and proteomics, demonstrated proficiency using, evaluating, and optimizing protein modeling and folding approaches, including Rosetta, AlphaFold3, and others. Demonstrated track record of scholarly excellence.

Required:

• Bachelor''s degree in biological science, computational / programming, or related area and / or equivalent experience / training.
• Minimum 3 years of related experience
• Thorough knowledge of bioinformatics methods, nextgen sequencing processing, applications programming, web development and data structures.
• Thorough knowledge of Python bioinformatics programming design, modification and implementation.
• Thoroughly proficient with design, implementation, and management of SQL relational databases, web interfaces, and linux based operating systems.
• Thoroughly proficient with modern LLM application development tools.
• Thorough knowledge of protein folding algorithms, including AlphaFold3and deploying packages on different hardware platforms, such as local systems and/or HPCs
• Thorough knowledge of machine learning techniques for building predictive classifiers, including logistic regression methods, random forest, neural networks, on multi-modal data, including mass spectrometry spectra, single cell sequencing, B cell repertoire sequencing, phage immunoprecipitation, yeast display, and similar.
• Proficient knowledge of basic cell biology, genomics, and basic immunology.
• Self-motivated, work independently or as part of a team, able to learn quickly, meet deadlines, and demonstrate problem-solving skills.
• Thorough knowledge of genomic alignment algorithms, including Diamond, Minimap2, STAR.
• Conceptual familiarity with PhIPseq, yeast display, and antigen screening methods.

Preferred:

• Ability to interface with management on a regular basis.

• Doctoral degree in biological science, computational / programming, or related area and / or equivalent experience / training. Ideally in machine learning applied to biomedicine areas.

Problem Solving:

• Given a large biologic dataset derived from cases and controls, construct and train a machine learning classifier, test performance on held out data, and derive key features driving classification performance
• Construct new query interfaces using APIs to commercial AI systems for analysis of large scale datasets, including agentic systems for automated data analysis and hypothesis generation
• Create a new client/server database for antigen display data, with data analysis and visualization tools.
• Analyze B or T Cell receptor repertoire sequencing data for clonal expansion
• Model antigen / antibody interactions using AlphaFold3

Less frequent and more complex problems solved by the employee:

• Troubleshooting SQL database issues, designing new web server frameworks.
• Build new databases as needed.
• Building bespoke visualization tools for new datasets

Problems/situations that are referred to this employee''s supervisor:

• Scientific strategic direction questions
• Collaboration strategy and agreements
• Acquisition of new patient cohorts for data production

%

of time

Essential Function (Yes/No)

Key Responsibilities

(To be completed by Supervisor)

25

YESApplies complex bioinformatics concepts to implementexisting software tools and systems, both command line and web based for large scale analysis of in-house generated genomic, proteomic, and immunology data. .

20

YESDevelops new analysis tools, focusing on automated analysis, data aggregation, hypothesis generation. May include agentic systems.

15

YESDevelops, implements, and maintains web interfaces and SQL databases to share and display bioinformatics analysis and content with collaborators and other users.

10

YESPerforms complex data modeling, performance and integration testing, and builds user interfaces for a variety of internal and external constituents.

20

YESPerforms complex data analysis, including developing predictive machine learning classifiers, for in-house generated data.

10

YESAssists with manuscript preparation, figure making, public data deposition

100%

(To update total %, enter the amount of time in whole numbers (without the % symbol - e.g., 15, 20) then highlight the total sum (e.g., 1%) at the bottom of the column and press F9. The total sum should add up to 100%.)

%

of time

Essential Function (Yes/No)

Key Responsibilities

(To be completed by Supervisor)

25

YESApplies complex bioinformatics concepts to implementexisting software tools and systems, both command line and web based for large scale analysis of in-house generated genomic, proteomic, and immunology data. .

20

YESDevelops new analysis tools, focusing on automated analysis, data aggregation, hypothesis generation. May include agentic systems.

15

YESDevelops, implements, and maintains web interfaces and SQL databases to share and display bioinformatics analysis and content with collaborators and other users.

10

YESPerforms complex data modeling, performance and integration testing, and builds user interfaces for a variety of internal and external constituents.

20

YESPerforms complex data analysis, including developing predictive machine learning classifiers, for in-house generated data.

10

YESAssists with manuscript preparation, figure making, public data deposition

100%

(To update total %, enter the amount of time in whole numbers (without the % symbol - e.g., 15, 20) then highlight the total sum (e.g., 1%) at the bottom of the column and press F9. The total sum should add up to 100%.)