Associate Director, Clinical Data Integration & AI Programming

Acadia Pharmaceuticals Inc.

41d•$158,000 - $197,900•Remote

About The Position

The Associate Director is a hands-on technical role responsible for automating how clinical data are integrated across assigned compounds and studies, and for building the reusable R and Python dashboards and data review tools that make those data usable by study teams. Working in R, Python, SQL, and APIs on the Posit platform, the role builds automated ingestion pipelines with incoming quality and congruency checks, maps disparate source structures into a standardized analysis-ready data model and delivers validated dashboards and review tools built on that foundation. It additionally evaluates and implements applied AI and generative AI capabilities where they measurably improve data processing, quality review, or programming productivity, always under human oversight and in accordance with regulations, SOPs, and data privacy requirements.

Requirements

Bachelor’s degree in statistics, biostatistics, computer science, data science, biomedical informatics or a related science field. An equivalent combination of relevant education and experience may be considered
Targeting 10 years of progressively responsible experience in statistical programming, clinical programming, clinical data engineering, or clinical analytics, preferably in a pharmaceutical or biotech environment. Demonstrated experience delivering technical solutions that span multiple studies is required
Advanced hands-on R programming, including Shiny, tidyverse, data.table, R Markdown/Quarto, package development, modular application design, and reproducible workflows
Strong hands-on Python for data ingestion, transformation, automation, analytics, and application development
Strong SQL proficiency and experience building and consuming REST APIs
Demonstrated experience developing and deploying interactive clinical dashboards, patient profiles, data review tools, or study monitoring applications used by study teams
Demonstrated experience designing automated ingestion, transformation, mapping, validation, and refresh processes for structured and semi-structured clinical data
Experience standardizing and integrating EDC, laboratory, eCOA, safety, IRT, and operational data across multiple studies or programs
Experience with Posit/RStudio Workbench, Posit Connect, and Posit Package Manager, or comparable enterprise R and Python environments
Experience with Git version control, automated testing, CI/CD, logging, monitoring, and controlled software deployment
Strong understanding of clinical trial data and CDISC standards, including SDTM, ADaM, metadata-driven programming, and integrated data structures
Working knowledge of SAS and the ability to bridge established SAS workflows with modern R and Python solutions
Practical understanding of GenAI, LLMs, RAG, and AI-assisted programming in regulated environments, including their limitations and validation implications
Strong knowledge of GCP, ICH, 21 CFR part 11, data privacy, access control, audit trails, and validation expectations for clinical data systems
Demonstrates strong written and verbal communication skills, conveying complex technical concepts clearly to technical and non-technical stakeholders
Balances competing priorities and deadlines, ensuring timely and high-quality execution across multiple initiatives
Willing and ability to travel domestically and internationally as needed

Responsibilities

Designs, builds, and maintains automated pipelines that ingest clinical data from EDC systems, central laboratories, eCOA and IRT vendors, safety systems, and other external providers at defined refresh frequencies, with scheduling, versioning, audit trails, processing logs, and failure alerting
Owns the standardized cross-study and cross-compound clinical data model that harmonizes source structures, terminology, and variables into consistent, analysis-ready form, and establishes metadata-driven mapping specifications so new studies and vendors onboard without rebuilding pipelines
Develops automated incoming data quality and congruency checks, including completeness, structural conformance, visit and date consistency, cross-domain reconciliation, duplicates, and outliers, and routes actionable exception outputs to Data Management and study teams
Automates laboratory, SAE, eCOA, and IRT reconciliation workflows and develops congruency flags that identify discrepancies across studies, compounds, and source systems
Develops algorithms and data feeds supporting risk-based monitoring and centralized data surveillance
Builds controlled APIs and data access components that provide consistent, governed access to standardized clinical data for dashboards and downstream programming
Designs, develops, validates, deploys, and maintains interactive R/Shiny and Python dashboards for clinical data review and study health monitoring, covering enrollment, adverse and serious adverse events, efficacy data review, laboratory trends, protocol deviations, visit compliance, data cleaning status, and operational metrics
Builds interactive patient profiles, data review listings, edit check outputs, coding review reports, and medical review applications, transitioning these deliverables from manual or SAS-based workflows into reproducible R/Posit solutions
Develops reusable R and Python packages, modules, visualization components, and dashboard templates, together with common metric definitions and navigation patterns, so outputs are consistent and comparable across studies and compounds
Develops automated study team communications, including scheduled summaries of enrollment, safety events, data cleaning status, and other key study metrics
Partners with Data Management, Clinical Operations, Clinical Development, Safety, Biostatistics, and Statistical Programming to translate clinical review needs into reliable, intuitive dashboard functionality and drives adoption through training and documentation
Operationalizes R/Posit capabilities within Biometrics, including Posit Workbench, Posit Connect, Package Manager, controlled package environments, application publishing, access management, and governed deployment
Establishes R and Python development standards covering modular design, reusable code libraries, code review, automated testing, error handling, logging, and dependency management, and applies Git version control and CI/CD practices to pipelines and applications
Owns the lifecycle of pipelines, dashboards, and reusable components from requirements and prototyping through validation, production release, monitoring, enhancement, and retirement, with documentation, traceability, and change control appropriate to a regulated environment
Applies established validation, documentation, and quality standards to assigned pipelines and applications, and supports audits and inspections as subject matter expert for the solutions the incumbent has built
Evaluates, prototypes, and implements AI and generative AI capabilities that measurably improve clinical data transformation, quality review, dashboard summarization, metadata and standards search, code generation and review assistance, or documentation drafting
Integrates approved LLM and retrieval augmented generation capabilities into R and Python applications where they deliver clear operational benefit and can be appropriately governed, including natural language querying of approved internal standards, specifications, and study documentation
Applies human in the loop review, predefined acceptance criteria, traceability, and validation to AI-assisted outputs, and determines when AI-assisted methods are appropriate versus when deterministic, validated programming is required
Executes the clinical data integration, dashboard, and automation roadmap across assigned compounds, and prioritizes work within an agreed backlog
Leads technical and process improvement initiatives within assigned compounds and workstreams, and recommends sourcing approaches and tooling for consideration by functional leadership
Provides technical oversight of FSP, CRO, vendor, and consultant resources supporting assigned data integration and dashboard development work, including specification, review, and acceptance of their deliverables
Partners with study teams, Data Management, and Biostatistics at the study and compound level to gather requirements, resolve issues, and drive adoption of delivered tools
Provides training, mentoring, and technical guidance to statistical and clinical programmers on R/Posit, Python, data automation, dashboard development, and responsible AI practices
Monitors developments in R, Python, Posit, clinical data engineering, and AI use in drug development, and recommends relevant advances for adoption
Other responsibilities as assigned.

Benefits

Competitive base, bonus, new hire and ongoing equity packages
Medical, dental, and vision insurance
Employer-paid life, disability, business travel and EAP coverage
401(k) Plan with a fully vested company match 1:1 up to 5%
Employee Stock Purchase Plan with a 2-year purchase price lock-in
15+ vacation days
13 -15 paid holidays, including office closure between December 24th and January 1st
10 days of paid sick time
Paid parental leave benefit
Tuition assistance