Remote PK/PD Modeling / Pharmacometrics Lead - AI Trainer ($150-$200 per hour)Mercor • Indio, California, United States

Cette offre d'emploi n'est plus disponible

Remote PK/PD Modeling / Pharmacometrics Lead - AI Trainer ($150-$200 per hour)

Mercor

Indio, California, United States

Indio, California, United States

Trouver des emplois similaires

À propos

This person complements the client’s “Translational / Clinical Pharmacology Decision-Maker” team by grounding dose selection and exposure–response analysis in **quantitative structure and parameter plausibility**. ### **Who we’re looking for** - Deep hands-on experience in **PK, PD, exposure–response modeling**, and ideally **population PK or QSP**. - Expert at model fitting, sensitivity analysis, and identifying non-plausible parameter spaces. - Can evaluate the validity of dose–exposure predictions and detect high-risk extrapolations. - Comfortable designing **model evaluation rubrics** that distinguish between acceptable vs. non-credible outputs. - Able to articulate how quantitative checks should complement narrative decision logic. **Nice-to-have:** - Experience supporting translational or clinical pharmacology leads in dose justification. - Familiarity with integrating nonclinical PK/PD data (2-species GLP → human FIH extrapolation). ### **Experience level** - ~8–12 years of quantitative pharmacology experience in **pharma, CROs, or modeling consultancies**. - Strong portfolio in **population PK/PD**, **exposure–response**, and **parameter estimation** using NONMEM, Monolix, or equivalent tools. - Demonstrated ability to interpret model results for decision-making, not just fit data. - Can create **fit-for-purpose models** and critique model structures or assumptions under uncertainty. ### **Expectations** - Design and refine **micro-evaluations** for PK/PD performance (curve fits, parameter checks, error taxonomies). - Encode **quantitative sanity checks** into model rubrics for automated evaluation. - Define **failure conditions** (e.g., unsafe extrapolation, poor coverage curves, invalid assumptions). **Inputs we give:** - PK/PD datasets, tox summaries, and performance prompts (e.g., “fit exposure–response curves, interpret safety margins”). - Example model outputs from automated systems. **Expected outputs:** - **Quantitative Rubrics:** clear thresholds for acceptable parameter fits, coverage curve quality, and model integrity checks. - **Golden Fit Examples:** representative “ideal” PK/PD model outputs and visualizations for calibration. - **Error Taxonomy:** structured list of typical modeling or fitting errors, with root-cause annotations. - **Meta-Layer Commentary:** short note per rubric capturing how expert modelers recognize implausible or unsafe fits beyond numeric error values. ### **Engagement Model & Compensation** - **Contract / part-time**, remote, outcome-based deliverables.

Indio, California, United States

Compétences linguistiques

English

Avis aux utilisateurs

Cette offre a été publiée par l’un de nos partenaires. Vous pouvez consulter l’offre originale ici.

Trouver des emplois similaires