About the role#
As a Computational Antibody Repertoire Analysis Co-Op, you will join the Biotherapeutics Research team to help build an NGS computational pipeline. This project focuses on prioritizing antibody hits to reduce attrition of non-binders and low-affinity binders. You will use somatic hypermutation models to infer B cell evolutionary trajectories and identify highly evolved clones from humanized mouse models. You will also work with scientists to benchmark models and create a reproducible pipeline that ranks higher-affinity candidates.
What you'll do#
- Curate, quality-control, and analyze antibody repertoire sequencing datasets.
- Benchmark somatic hypermutation models and related computational methods.
- Evaluate model calibration, predictive performance, uncertainty, and generalization.
- Apply immune-repertoire analysis tools such as Shazam and Dowser.
- Contribute to an end-to-end sequence-prioritization workflow.
- Explore whether SHM-based features can be complemented by protein language models or other machine-learning approaches.
- Develop reproducible analyses using version-controlled code.
- Collaborate with computational and laboratory scientists.
- Summarize results, limitations, and recommendations in presentations and reports.
What you'll need#
- Current enrollment as an undergraduate, graduate, or advanced degree student in an accredited program.
- Major or minor in Biology, Computer Science, or Data Science.
- Undergraduate students must have completed at least 12 credit hours; graduate students must have completed at least 9 credit hours.
- Cumulative GPA of 3.0 or higher is preferred.
- Experience programming in Python or R.
- Familiarity with biological sequence analysis, genomics, immunology, antibody biology, or immune-repertoire sequencing.
- Understanding of core statistical and machine-learning concepts.
- Ability to work with command-line tools and Git.
- Experience with immunoglobulin sequence annotation, clonotype assignment, or somatic hypermutation modeling.
- Familiarity with AIRR Community standards or tools like Change-O, Shazam, Dowser, IgBLAST, or MiXCR.
- Experience analyzing single-cell V(D)J data or bulk antibody repertoire sequencing data.
- Experience with high-performance computing, cloud computing, containers, workflow managers, SQL, or data visualization.
- Must be 18 years of age or older and legally authorized to work in the United States without restriction.
- Willingness to complete a drug test and post-offer physical.
Location & details#
- Location: Ridgefield, Connecticut, United States.
- Modality: On-site.
- Term: Rolling.
- Employment: Full-time paid co-op.
About Boehringer Ingelheim
Boehringer Ingelheim develops pharmaceutical products for humans and animals. The company operates within the pharmaceutical manufacturing industry. It was founded in 1885 and maintains its headquarters in Ingelheim am Rhein, Germany. The organization is privately held and employs over 10,000 people.
How to get in at Boehringer Ingelheim
Applying early to Boehringer Ingelheim gives you a clear advantage before the applicant pool becomes unmanageable. Intern Insider sends an instant alert the moment a role matching your target is published anywhere, so you apply among the first and get seen before the pile grows. Reaching out to the right people often yields better results than submitting to a general queue. Intern Insider surfaces the recruiters behind the company roles so you can contact them directly to ask about the position or a referral, which materially improves your response rates.
