Engineer - Mlops & Scientific Platforms - Data Foundry

Engineer - MLOps & Scientific Platforms - Data Foundry

At Lilly, we unite caring with discovery to make life better for people around the world. We are a global healthcare leader headquartered in Indianapolis, Indiana. Our employees around the world work to discover and bring life-changing medicines to those who need them, improve the understanding and management of disease, and give back to our communities through philanthropy and volunteerism. We give our best effort to our work, and we put people first. We're looking for people who are determined to make life better for people around the world.

Location: San Diego, CA; San Francisco, CA; Boston, MA; Louisville, CO; Indianapolis, IN

Reports To:

Lead, Scientific Software Engineering (R7–R9), Architecture4Insight

We are seeking an Engineer - MLOps & Scientific Platforms - Data Foundry to operationalize Data Foundry's scientific tools and analytical methods into actionable-prototypes. You will build the ML deployment pipelines, model serving infrastructure, API layers, and observability guardrails that make our scientific discovery methods and tools reliable, scalable, and consumable, both by discovery scientists and by the Frontier AI group's autonomous agents.

This role sits at the interface between Methods4Insight (which develops analytical methods) and Architecture4Insight (which provides the agile data infrastructure). Your job is to ensure every scientific tool Data Foundry produces are analytics-ready, well-monitored, and exposed through APIs with the response-time guarantees and error handling that both human users and AI agents require.

MLOps & Model Lifecycle Management

• Build and maintain end-to-end ML deployment pipelines: experiment tracking, model versioning (MLflow, Weights & Biases), containerized model serving, and automated retraining triggers.
• Develop model registry infrastructure and feature engineering pipelines that enable computational scientists to access models.
• Implement monitoring and alerting for data pipelines, APIs, ML models, and agentic systems (LLMOps) to ensure system reliability and performance at scale.
• Build dashboards and metrics tracking for pipeline execution, API latency, token usage, model prediction quality, and system health
• Establish structured logging and tracing infrastructure for debugging and performance optimization across scientific data systems

Scientific Tool Agile Deployment

• Deploy predictive and analytical methods from Methods4Insight (e.g. cheminformatics, structural biology, bioinformatics, reaction informatics) with versioning, structured error handling, and response-time guarantees that enable insight generation in agile manner. Productionize when and where needed in partnerships with Tech@Lilly.
• Build serving infrastructure supporting both synchronous (interactive scientist queries) and asynchronous (batch and agent-invoked) workloads in partnership with Tech@Lilly and Frontier AI.
• Define and implement API contracts, documentation standards, and testing frameworks that ensure scientific tools are analysis ready, robust and consumable by external teams including Frontier AI.

Platform Engineering & Integration

• Build and operate cloud-native model serving infrastructure (AWS, Azure, or GCP) using containers, Kubernetes, and infrastructure-as-code.
• Develop CI/CD pipelines for ML models: automated validation, A/B testing, canary deployments, and rollback procedures.
• Integrate model serving with Data Foundry's data pipelines, ensuring models have access to properly formatted, versioned training and inference data.

Frontier AI Interface & Collaboration

• Partner with the Frontier AI team and Tech@Lilly to ensure Data Foundry's scientific tools are exposed via well-defined interfaces (REST APIs, MCP-compatible endpoints) that agents can invoke programmatically.
• Collaborate on API performance requirements: latency targets, throughput guarantees, and graceful degradation under load.
• Work with Methods4Insight scientists to ensure deployed models include appropriate uncertainty quantification and confidence metrics.

Basic Requirements

• B.S. or M.S. in Computer Science, Data Science, Machine Learning, Bioinformatics, Computational Biology, or related field.
• 3+ years of experience in MLOps, ML engineering, or scientific platform development
• Qualified applicants must be authorized to work in the United States on a full-time basis. Lilly will not provide support for or sponsor work authorization or visas for this role, including but not limited to F-1 CPT, F-1 OPT, F-1 STEM OPT, J-1, H-1B, TN, O-1, E-3, H-1B1, or L-1.

Preferred Qualifications

• Pharmaceutical or biotech research industry experience.
• Strong Python skills; experience with ML frameworks (PyTorch, TensorFlow, scikit-learn) and ML lifecycle tools (MLflow, W&B, Kubeflow, or similar).
• Proven track record building and deploying production model serving infrastructure — containerized endpoints, RESTful/gRPC APIs, and operational monitoring
• Working knowledge of cloud platforms (AWS, Azure, or GCP), Kubernetes, and CI/CD automation.
• Strong communication skills with ability to collaborate across computational scientists, software engineers, and partner teams.
• Experience operationalizing scientific or computational models (cheminformatics, bioinformatics, structural biology, QSAR, molecular simulations, PK/PD, systems biology, or ODE-based models).
• Hands-on experience with model monitoring, drift detection, and automated retraining systems.
• Familiarity with API gateway patterns, event-driven architectures, and service mesh technologies.
• Experience with feature stores, data versioning (DVC), or experiment tracking at scale.
• Exposure to AI agent frameworks (MCP, LangChain) or building APIs that AI systems invoke programmatically.
• Experience with C, C++, CUDA, or GPU-accelerated computing for optimizing model training/inference performance; familiarity with containerizing HPC workloads (Singularity/Apptainer).