Description

About Norstella:

Norstella is a premier and critical global life sciences data and AI solutions provider dedicated to improving patient access to life-saving therapies. Norstella supports pharmaceutical and biotech companies across the full drug development lifecycle — from pipeline to patient. Our mission is simple: to help our clients bring therapies to market faster and more efficiently, ultimately impacting patient lives.

Norstella unites market-leading brands - Citeline, Evaluate, MMIT, Panalgo, Skipta and The Dedham Group and delivers must-have answers and insights, leveraging AI, for critical strategic, clinical, and commercial decision-making. We help our clients:

• Accelerate the drug development cycle
• Assess competition and bring the right drugs to market
• Make data driven commercial and financial decisions
• Match and recruit patients for clinical trials
• Identify and address barriers to therapies

Norstella serves most pharmaceutical and biotech companies around the world, along with regulators like the FDA, and payers. By providing critical proprietary data supporting AI-driven workflows, Norstella helps clients make decisions faster and with greater confidence. Norstella’s investments in AI are transforming how data is consumed and decisions are made, disrupting inefficient legacy workflows and helping the industry become more efficient, innovative, and responsive to patient needs.

Job Description

As a Senior Life Sciences Analyst for Model Training at Norstella, you will sit at the intersection of deep clinical and 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 the preference and judgment layer of model development — through scoring and ranking outputs, you will calibrate models on dimensions of quality, accuracy and clinical reasoning such that they are able to handshake with persona use cases. Your judgment becomes the signal that bridges a capable model and a genuinely useful one, and will play a critical role in our efforts to deliver predictive analytics and insights across clients.

Travel: None required

Responsibilities

• Evaluate model outputs across clinical, regulatory, and life sciences tasks by rating individual responses, ranking pairs and lists, and rewriting outputs to demonstrate the preferred response.
• Define and maintain evaluation rubrics, preference dimensions, and quality criteria (factual accuracy, clinical reasoning quality, etc) that govern model outputs and preference alignment.
• Act as an expert-in-the-loop for how life science models are commercialized with clients, including ongoing support for implementation.
• Advise and assist with interpretation of model behavior, bridging the desired behavior back to the dataflow inflection point, working with the relevant teams to adjust as needed.
• Partner with data scientists and MLEs to walk feedback into data collection pipelines.
• Conduct red-team and adversarial evaluation of models, surfacing subtle failure modes — hallucinations, citation errors, unsupported clinical claims, regulatory missteps — that automated metrics cannot reliably catch.
• Analyze preference data and model behavior to identify systematic gaps, then partner with the fine-tuning SMEs and the data science team to decide how each gap is addressed through preference data.
• Conduct new proofs of concept for novel domain capabilities.
• Contribute to Norstella’s knowledge graph and taxonomy work and help design new agentic workflows based on domain-grounded language models.