Data Scientist- Machine Learning(Pharma Experience & W2 Only)

Job Title: Senior Data Scientist / Machine Learning (Advanced Analytics – Clinical Development) Location:Remote Duration of Contract: Long Term Role Summary We are seeking a Senior Data Scientist specializing in Machine Learning to join our Advanced Analytics team supporting clinical research and development. This role focuses on delivering highimpact analytics that influence trial strategy and program decisions. The successful candidate will independently lead endtoend analytical work—framing ambiguous questions, shaping data into analysisready form, applying robust statistical and machine learning methods, and communicating insights clearly to stakeholders. We are looking for someone with at least 4 years of professional experience as a data scientist/analyst in a pharma or related setting. Key Responsibilities  Lead complex clinical analytics: Own analyses across clinical studies and related data sources, tackling problems where the path is not predefined and the work requires strong judgment and rigor.  Partner with stakeholders: Proactively engage clinical, biometrics, and crossfunctional partners to gather requirements, align on analytic intent, refine questions, and deliver decisionready outputs.  Build statistical + ML solutions: Select, develop, and validate appropriate statistical approaches and machine learning models to answer clinical development questions; ensure interpretability and defensibility of results.  Work with pharmacology-adjacent data: Integrate and analyze clinical outcomes with exposure/response or other pharmacologyrelated datasets where relevant to the question.  Engineer data at scale: Perform data wrangling, feature engineering, and reproducible pipelines in modern compute environments (Microsoft Fabric or similar); write productionquality analysis code and adhere to team standards.  Operate within clinical data standards: Work effectively within industry clinical data conventions and structured clinical data models; ensure analysis specifications and outputs align with quality expectations.  Tell a clear story: Present compelling, validated narratives and visuals that translate complex analytics into insights stakeholders can act on.  Be a team multiplier: Collaborate effectively, mentor where appropriate, and contribute to a culture of strong teamwork, responsiveness, and continuous improvement. What Success Looks Like  You take ownership without waiting for perfect direction, and you bring structure to ambiguity.  Stakeholders trust you because you communicate early, set expectations, and deliver rigorous, understandable work.  You can work independently and collaborate smoothly across functions, strengthening partnerships and repeat engagement. Core Qualifications  Demonstrated track record delivering analytics in clinical research settings, including working with latestage clinical datasets and typical clinical development constraints (e.g., endpoint complexity, protocol nuance, data quality realities).  Strong foundation in statistical reasoning with practical experience applying predictive/ML methods in healthcare/clinical contexts (beyond academic exercises).  Proficiency in Python or R, with the ability to handle large, complex datasets in distributed or cloud-enabled environments (e.g., Spark-based workflows).  Comfort working within structured clinical data standards/models and producing analysis outputs that meet quality expectations in regulated environments.  Strong communication skills: ability to explain methods, assumptions, and results clearly to both technical and nontechnical audiences.  Highly collaborative with strong interpersonal skills; able to build credibility and maintain productive stakeholder relationships over time. Nice to Have  Experience supporting programs in one or more of the following therapeutic domains: oncology, dermatology, hematology (or similarly complex disease areas).  Experience with time-to-event or longitudinal modeling, and/or methods for explaining model outputs to non-technical partners (e.g., interpretable ML, model diagnostics, clear visualization). Working Style / Leadership Expectations  Self-starter mindset with strong ownership, organization, and followthrough.  Ability to lead analytical workstreams, influence without authority, and deliver in a matrixed environment.