Principal Prediction & Insights Applications Engineer, Small & Large-Molecule Discovery

Working with Us
Challenging. Meaningful. Life-changing. Those aren’t words that are usually associated with a job. But working at Bristol Myers Squibb is anything but usual. Here, uniquely interesting work happens every day, in every department. From optimizing a production line to the latest breakthroughs in cell therapy, this is work that transforms the lives of patients, and the careers of those who do it. You’ll get the chance to grow and thrive through opportunities uncommon in scale and scope, alongside high-achieving teams. Take your career farther than you thought possible.

Bristol Myers Squibb recognizes the importance of balance and flexibility in our work environment. We offer a wide variety of competitive benefits, services and programs that provide our employees with the resources to pursue their goals, both at work and in their personal lives. Read more: careers.bms.com/working-with-us.

Summary:

Own the strategy and delivery of GenAI-native applications, predictive-model workflows, and insight-driven analytics platforms that accelerate both small-molecule and biotherapeutic invention. Translate scientific objectives into intuitive software products and robust model-ops practices that help chemists, protein engineers, and data scientists iterate faster, uncover deeper insights, and make better decisions.

Domain-Centric AI / ML Enablement:

• Champion predictive-model use-cases across medicinal chemistry and biologics (e.g., property prediction, sequence optimization, generative design).

• Harness cutting-edge structure- and sequence-prediction models (AlphaFold/OpenFold, RoseTTAFold, RFdiffusion, Schrodinger, OpenEye) to accelerate target triage, protein engineering, and binding-interface analysis.

• Track, evaluate, and train molecular prediction models and integrate genAI methods in the literature and open-source community.

• Ensure model outputs, metrics, and explainability align with discovery KPIs and downstream lab workflows.

Insight-Driven Agentic Gen-AI and Applications:

• Integrate agentic genAI frameworks (e.g., Bedrock, LangChain, LlamaIndex, AzureOpenAI) to create conversational analytics, automated report writers, and “copilot” agents that guide scientists through complex SAR, sequence, or imaging datasets.

• Deliver full-stack applications—React/Next.js fronts with Python/FastAPI & GraphQL services—that surface models and analytics at scale with sub-second responsiveness.

Model-Ops & Engineering Excellence:

• Stand up automated pipelines for data curation, experiment tracking, CI/CD, and governed model release (PyTorch/TensorFlow + MLflow/Kubeflow/SageMaker + GitHub Actions).

• Package and deploy predictive applications and model endpoints to cloud PaaS or on-prem containers for scalable inference and performant access.

• Codify reusable templates, inner-source libraries, and design systems that cut feature time-to-value by 40%.

Leadership & Collaboration:

• Mentor a cross-disciplinary team of full-stack and ML engineers; foster “better-than-best” practices in code quality, documentation, and UX research.

• Partner with discovery leads, IT operations, and external vendors to align technical backlogs with portfolio milestones and data-quality standards.

• Influence budgeting and make-vs-buy decisions for AI tooling and platform enhancements.

Qualifications:

• Deep Discovery Context – 8-10 yrs building software or ML solutions for medicinal chemistry, biologics engineering, or high-content screening; fluent in SAR data, sequence/structure relationships, and assay lifecycles.

• Molecular Tooling Familiarity - Practical mastery of open-source and proprietary molecular-design toolkits (e.g., EvoDiff, RFdiffusion, Molformer, RDKit, Alphfafold, Schrodinger, OpenEye) and the ability to integrate or adapt them within proprietary pipelines.

• Hands-on GenAI / ML depth – Demonstrated success fine-tuning and deploying LLMs, diffusion models, GNNs, structure-prediction models (AlphaFold family, RoseTTAFold, ESMFold), or vision transformers for scientific or operational use-cases.

• Modern MLOps – IaC (Terraform/CloudFormation), automated testing, secrets management, continuous model evaluation, lineage tracking

• Influence & communication – lead architecture reviews, map tech choices to scientific KPI