Senior Life Sciences Engineer

Senior Life Sciences Knowledge Engineer

About us:

Why Norstella? Norstella unites market-leading companies that all have a shared 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 our clients:

• Assess the market need and competitive landscape
• Know precisely which drugs to prioritize in their portfolios
• Find out where the launch difficulties will be-before they're difficulties
• Track and improve market access post-launch

By combining the efforts of each organization under Norstella, we can offer an even wider breadth of expertise, cutting-edge data solutions and expert advisory services alongside advanced technologies such as real-world data, machine learning-driven predictive analytics. At Norstella, we don't just deliver information and insights. We deliver answers you can act on.

Job Description

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, but will interface across cross-functional teams of data scientists, machine learning engineers and data engineers. Your work centers on curating high-quality fine-tuned datasets which speak to the desired end-to-end behavior we want a model to internalize.

The datasets and annotation guidelines/frameworks that govern it will play a critical role in our efforts to deliver predictive analytics and insights across clients.

Responsibilities:

• Translate complex clinical, regulatory, and life sciences subject matter expertise/requirements 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.
• Through close collaboration between SME and technical colleagues, develop novel methods and parameters of model behavior, 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 the annotation and labeling guidelines that govern dataset construction, ensuring the schema, vocabulary, and definition of "what good output looks like" remain consistent 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 across NPD.
• Train and enable subject matter expert graders running eval rounds, including translating feedback to how data scientists implement improvements at the tool call layer.
• Run iterative dataset experiments: identify where the model is failing, design targeted example slices to close those gaps, and partner with the human-in-loop SMEs to measure the impact of each dataset change.
• 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.

The guiding principles for success at Norstella:

• Bold, Passionate, Mission-First
• Integrity, Truth, Reality
• Kindness, Empathy, Grace
• Resilience, Mettle, Perseverance
• Humility, Gratitude, Learning

Qualifications:

• 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 with 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 data…