Senior Life Sciences Knowledge Engineer

Norstella unites market-leading companies that share a goal of improving patient access. Each organization (Evaluate, Citeline, MMIT, Panalgo, The Dedham Group) delivers must-have answers for critical strategic and commercial decision-making. Together, we help clients assess the market need and competitive landscape, prioritize drugs in their portfolios, identify launch difficulties before they arise, and track and improve market access post-launch. By combining expertise, cutting-edge data solutions, expert advisory services, and advanced technologies such as real-world data and machine learning-driven predictive analytics, Norstella delivers actionable answers.

About the role

As a Senior Life Sciences Knowledge Engineer at Norstella, you will sit at the intersection of deep scientific domain expertise and applied AI development. This role will be embedded within a group of life science thought leaders while interfacing across cross-functional teams of data scientists, machine learning engineers, and data engineers. Your work centers on curating high-quality fine-tuned datasets that define the desired end-to-end behavior of AI models, playing a critical role in delivering predictive analytics and insights to clients.

Responsibilities

• Translate complex clinical, regulatory, and life sciences subject matter expertise into repeatable patterns that can be taught to a model through gold standard examples, working closely with data scientists and machine learning engineers to shape the model’s schema, vocabulary, and target behavior.
• Develop novel methods and parameters of model behavior through collaboration between subject matter experts (SMEs) and technical colleagues, based on interpretation of requirements and quick iteration cycles.
• Design, build, and continuously refine fine-tuning datasets consisting of input/output pairs that demonstrate desired end-to-end behavior across the target task surface area, edge cases, and known failure modes.
• Author and maintain annotation and labeling guidelines that govern dataset construction, ensuring consistency in schema, vocabulary, and definition of “what good output looks like” across contributors.
• Define the task taxonomy and output schema in close partnership with data scientists, ensuring data architecture aligns with downstream evaluation metrics and production requirements.
• Train and enable SME graders running evaluation rounds, including translating feedback to data scientists for improvements at the tool call layer.
• Run iterative dataset experiments: identify model failures, design targeted example slices to close gaps, and partner with human-in-loop SMEs to measure the impact of dataset changes.
• Maintain provenance, licensing, and compliance documentation for every dataset, ensuring all training data meets GxP, regulatory, and intellectual property standards expected in life sciences and clinical settings.
• Conduct new proofs of concept for novel domain capabilities.
• Contribute to Norstella’s knowledge base and taxonomy work, and help design new agentic workflows based on domain-grounded language models.

Qualifications

The skills you bring to the table:

• Graduate degree in life sciences, medical sciences, computer science, or equivalent professional experience.
• At least 3 years of professional experience in production-grade life science datasets, including AI-enabled applications.
• Experience working with structured publishing platforms and data tools; comfort with automation concepts.
• Experience working with and statistically analyzing large and complex datasets, including data cleaning and preprocessing.
• Experience working with Generative AI, especially LLMs, including agents, throughout the entire software development lifecycle (SDLC).
• Experience creating MCPs (Model Configuration Packages) and consuming them into agentic workflows.
• Excellent problem-solving skills and the ability to work independently.
• Excellent communication skills, especially between technical and non-technical teams.

Skills

Bonus Points If You Have:

• Experience in developing, evaluating, deploying, and monitoring algorithms and models from proof-of-concept through production in a reproducible, auditable, GxP-compliant manner.
• Experience with the AWS ecosystem, specifically services like S3, ECS, API Gateway, SageMaker, and Bedrock.
• Familiarity with CI/CD processes, especially as applied to ML operations (MLOps), preferably with Azure DevOps.
• Experience in fast-paced novel development cycles.

Benefits

• Medical and prescription drug benefits
• Health savings accounts or flexible spending accounts
• Dental plans and vision benefits
• Basic life and AD&D benefits
• 401k retirement plan
• Short- and Long-Term Disability
• Education benefits
• Paid parental leave
• Paid time off