Build the automation layer for clinical trials.

The role

We're hiring a Senior/Principal Biostatistician to translate the biostatistics and statistical programming workflows you've spent a career mastering into the automation logic at the heart of our product. You'll work directly alongside our statistical programmers, biostatistics SMEs, and engineering team, sharing ownership of the domain skills that power the engine — and making sure they hold up in real clinical-trial workflows. We want someone driven to translate their expertise rather than re-execute it, and to help define how this work gets done for the next decade. This role reports to our Executive Director of Biostatistics.

What you'll do

• Author the domain skills that power the engine: modular automation that encodes real statistical workflows and decision logic across SAP authoring, SDTM review, ADaM specification and programming, TLF shell annotation, and TLF programming/review.
• Set the standard the platform conforms to: ensure outputs are operationally realistic, consistent with industry practice, and credible to sponsors and regulators, including consistency between the skills you author and those authored by others.
• Turn analysis requirements into product: partner with engineering and product to translate clinical analysis needs into features, with detailed specs and tight iterative feedback through every development cycle.

What we're looking for

• Experience: 7+ years leading and executing the biostatistics and statistical programming components of clinical trials.
• Regulatory fluency: deep command of the guidelines governing statistical analysis in the clinical-trial space, and an instinct for what a reviewer might flag.
• CDISC mastery: fluent in SDTM, ADaM, and the supporting metadata and documentation that make them a complete, submission-ready package.
• Adaptability: you've managed mid-study changes of varying scope — protocol amendments, CRF amendments — and you know how they ripple downstream into the analysis.
• Range: comfortable with the adjacent documents that shape statistical preparation even when biostatistics doesn't author them — study protocols, CRFs, EDC build specs, external vendor transfer agreements.
• Conviction: you'd rather encode your expertise , at a standard and level of quality you fully believe in, than re-execute it for the hundredth study. You want to set the standard, not absorb the inefficiency one more time.

Why join now

This is an exciting time in the pharmaceutical industry, as companies work towards technological advances and efficiencies. At idaptiq, we have proven founders with deep domain expertise covering biostatistics in clinical trials, AI/ML products in regulated healthcare environments, and building billion dollar software data businesses. They’ve brought together an amazing cross functional team of domain experts and engineers who are actively working to bring the idaptiq platform to life. Additionally, we have active design partnerships with established CROs, where we’re able to get direct user feedback to ensure we’re building a product that our users love in the context of real-world clinical trial biostatistic workflows. You'd be among the earliest and most impactful SME voices in the company, defining the function rather than inheriting it.

Apply for this role

This role will contribute to the translation of biostatistical and statistical programming workflows into structured automation logic within the product. You will work directly with a team of statistical programmers and biostatistics SMEs, sharing the responsibility for developing the domain “skills” that power the automation engine.

Working closely with the engineering team, you will ensure the skills created will integrate easily into real-world clinical trial workflows while delivering meaningful expertise across dataset specifications, code, and analysis outputs.

Product Collaboration

• Partner closely with engineering and product teams to translate domain requirements into product features.
• Help prioritize roadmap items based on automation impact and workflow value, including core modules and supportive features (CDISC compliance, independent validation workflows, replicate code into additional languages, aCRF automation, pooled analyses, etc.).
• Provide detailed specifications and iterative feedback during development cycles, including a focus on consistency between skills you author and those authored by others.

Automation Skill Development and Industry Alignment

• Guide the development of modular automation skills that encode statistical workflows and decision logic.
• Ensure outputs are operationally realistic and consistent with industry practice.
• Ensure platform outputs remain compliant and credible for sponsors and regulators.

Requirements

• 4+ years’ experience leading and executing the statistical programming components of clinical trials using SAS software:
  • Includes SDTM specification authoring/review, SDTM and ADaM dataset programming, TLF programming of at least moderate complexity, and CDISC submissions package contributions
  • Includes programming QC of datasets and outputs, acting as an independent validator
• Provide in-depth expertise in the areas of:
  • CDISC standards for SDTM, ADaM, and supporting metadata/documentation
  • SAS program and log review, including diagnosis of log findings leading to incorrect/incomplete analyses, improvement of coding efficiency, and the ability to evaluate alternative SAS coding approaches for accuracy and efficiency.
  • Data connectivity from raw sources and documentation to SDTM and ADaM (External vendor data, Case Report Forms (CRFs), EDC build specifications, use of Controlled Terminology, etc.)

Apply for this role

This role will contribute to the core engineering of idaptiq's automation platform — the systems that take SAPs, SDTM specifications, and ADaM designs as inputs and produce validated datasets, code, and analysis outputs as deliverables. You will work directly with a team of engineers, biostatistics SMEs, and statistical programmers, sharing the responsibility for building the agent architecture, evaluation infrastructure, and data pipelines that turn domain expertise into product capability.

Working closely with domain experts, you will ensure the platform delivers outputs that are operationally realistic, reproducible, and credible to sponsors and regulators — while maintaining the audit trails, validation evidence, and compliance posture required to operate inside CRO and biopharma environments.

Agent and Platform Engineering

• Design and build the agent systems that execute clinical trial automation skills end-to-end, including planning, tool use, retrieval, code generation, and verification loops.
• Develop the evaluation, observability, and regression testing infrastructure needed to ship agent behavior changes with confidence in a regulated context.
• Build the data plane that handles study data through the SDTM → ADaM → TFL pipeline, with strong guarantees around lineage, reproducibility, and auditability.

Product Collaboration

• Partner closely with biostatistics and statistical programming SMEs to translate domain skills into reliable agent workflows and reusable platform primitives.
• Help prioritize roadmap items based on automation impact and workflow value, including core modules and supportive features (independent validation workflows, code replication across languages, aCRF automation, pooled analyses, etc.).
• Provide detailed technical specifications and iterative feedback during development cycles, including a focus on consistency across the agent and skill surface area.

Compliance and Industry Alignment

• Build platform capabilities that meet GxP, 21 CFR Part 11, and CSV/GAMP5 expectations — including audit trails, access controls, validation evidence, and change management.
• Ensure platform outputs remain compliant and credible for sponsors and regulators.
• Contribute to security and compliance posture (SOC 2, customer audits) as the platform scales into CRO and biopharma deployments.

Requirements

• 7+ years building production software systems, with meaningful recent experience shipping LLM- or agent-based products:
  • Includes hands-on work with modern agent architectures (tool use, planning, retrieval, evaluation), not just thin wrappers around a chat API
  • Includes responsibility for evals, observability, and the engineering practices that make non-deterministic systems reliable
• Provide in-depth expertise in at least one of the following regulated-domain environments:
  • Health tech / life sciences (clinical trials, EHR, claims, provider data, HIPAA / GxP / 21 CFR Part 11)
  • Fintech or other regulated data/infrastructure environments (SOX, PCI, bank-grade audit and controls)
• Strong backend and data engineering foundation:
  • Comfortable owning data pipelines, schema design, and storage architecture for sensitive customer data
  • Comfortable operating cloud infrastructure (AWS preferred) with attention to tenancy, key management, and least-privilege access
• Track record of building products where correctness, auditability, and trust matter more than velocity-at-all-costs — and an instinct for how to ship quickly anyway.

Apply for this role