Build and scale enterprise AI assistant skills for drug development program management, portfolio, governance, and planning processes. Design agent workflows, shared knowledge layers, evaluations, permissions, approvals, and audit controls. Partner with process owners and technical teams to deploy trustworthy AI systems, measure quality and business impact, support regulated and Responsible AI requirements, and coach early-career colleagues. The role emphasizes solving business problems with AI tools while reducing hands-on coding.
Salary Range:
Job Description Summary
This is a hands-on senior role in the Data Science & AI (DSAI) team within Process Innovation, part of Strategy, Program & Portfolio Operations (SPPO) in Novartis Global Drug Development. Your focus is how Development works: the programme management, portfolio, governance and planning processes that move medicines from decision to decision. You will build, evaluate and scale AI skills for the assistants colleagues already use every day, such as Microsoft Copilot Cowork and Claude Cowork. These skills are built in language rather than code: instructions, checklists, templates and knowledge that tell the assistant how to do a real piece of SPPO work well.The role centres on three questions that decide whether these skills create value. What knowledge do they need, and how do we organise it so every skill draws on the same trusted sources? How do we review and evaluate skills at scale, rather than one by one? And how do we earn enough trust to let skills act (drafting and updating documents, records and messages) rather than only advise? We are looking for an engineer who wants to code less and solve more business problems. You will build with AI tools such as Claude Code, GitHub Copilot or AWS Kiro, and your engineering foundations are what let you design the system flow and the knowledge layer underneath each skill.
Job Description
Major accountabilitiesSkill design: building in language- Design and build skills for enterprise AI assistants (Microsoft Copilot Cowork, Claude Cowork) in which language is the programming interface: instructions, function-specific checklists, worked examples, templates and references to trusted sources.
- Translate SPPO processes and decisions, such as tollgate and governance reviews, development plan checks, portfolio reporting and programme documentation, into precise, testable skill specifications, working directly with the programme leaders and process owners who run them.
- Design how work flows across skills, agents and tools: what each step sees, what it produces, and where a human checks or decides. Apply agent-to-agent (A2A) patterns where skills in Copilot, Claude and other agents need to hand work to each other, with clear contracts for what is passed and who is accountable.
- Use AI building tools (Claude Code, GitHub Copilot, AWS Kiro) to author, test and maintain skills and the code around them, such as connectors, data preparation and evaluation harnesses, keeping each skill versioned, documented and correctly classified for the data it handles.
- Recognise when a need has outgrown a skill, and hand it over to the agentic engineering, product or platform teams with a clear evaluation record.
- Organise the knowledge skills draw on into a shared, trusted layer: checklists, definitions, templates, guidance and reference documents, curated once and reused by every skill rather than copied into each.
- Decide what goes on the platform: specify which trusted sources skills need and how they are exposed, through Model Context Protocol (MCP) servers and approved connectors that DDIT builds and runs. Design the data structures and patterns behind this layer so skills reach the right sources in SharePoint, Teams and business systems with the right access, provenance and freshness, and so each source serves many skills rather than one use case.
- Keep this knowledge maintained, owned and versioned, so that a change to a checklist or guideline flows to every skill that uses it.
- Build evaluation for every skill: test cases drawn from real documents, expert reference answers, and structured review (including AI-assisted grading checked against human experts), re-run whenever a skill changes.
- Measure what matters for the decision: correctness against expert judgement, coverage, hallucination and omission rates, consistency, and honest reporting of uncertainty.
- Make evaluation repeatable, so that review scales with the number of skills rather than the number of reviewers, and monitor skills in use for quality and drift.
- Contribute to DSAI evaluation standards, working with the Director, AI Systems Engineering & Evaluation.
- Define the path from advising to acting for each skill (read, draft, propose, act with approval, act on its own) and the evidence needed to move up a level.
- Set the guardrails for skills that write back, such as updating a document, a SharePoint list or a tracker, or sending a message: least-privilege access, previews, human approval points, reversibility and a clear audit trail.
- Ensure systems that act meet GxP, data privacy and Responsible AI requirements, working with Quality, Compliance and DDIT.
- Embed with SPPO teams (Global Program Management, portfolio, governance and operations) and the Process Innovation team, starting from the process and the decision rather than the technology: use design thinking and Lean methods to understand the work, find where skills can change how it runs, then land them in real use and measure their adoption and impact.
- Coach early-career scientists on rotation in AI-native building and evaluation, and share practice internally and externally through publications, conferences and communities of practice.
- Run skill building as a factory rather than one-off support: shared intake and triage, reusable components and patterns, and a maintained register of every system with its business owner, evaluation status and measured value.
- Skills in active use, number of users, and time from request to first use.
- Evaluation coverage: share of skills with maintained test cases and regression checks, and performance against expert review.
- Write-back readiness: skills moved to a higher level of autonomy on documented evidence, with no unreviewed incidents.
- Reuse of shared knowledge and skill components, and a complete register of skills with owner, evaluation status and measured value.
- Measurable impact on how Development runs: cycle time, effort saved and quality of decisions in SPPO processes.
- 6+ years as a software, data or ML engineer or data scientist, building systems that people rely on, with a clear wish to spend less time writing code and more time solving business problems.
- Demonstrable recent work building skills, agents or workflows for AI assistants (for example Microsoft Copilot or Claude), including how you checked that they worked.
- Experience of structured evaluation (designing test cases, working with expert reviewers, judging quality on evidence) and the ability to write specifications precisely.
- Solid engineering foundations: you read and write code (Python or similar), design how data and steps flow through a system, and work with the data models, APIs and connectors behind a knowledge layer, including MCP servers and agent-to-agent (A2A) integration patterns.
- Degree in computer science, engineering, or a quantitative or life science with strong technical depth; a postgraduate degree is an advantage.
- Experience of drug development governance, programme management or portfolio processes, ideally in a regulated (GxP) environment.
- Daily use of AI building tools such as Claude Code, GitHub Copilot or AWS Kiro, to build faster without losing understanding of the system.
- Experience with process improvement or design methods (Lean, Six Sigma, design thinking).
- Skill design for enterprise AI assistants (Microsoft Copilot, Claude)
- Precise writing: specifications, instructions and checklists
- Evaluation: test design, expert review and grading
- System flow design, data modelling and knowledge organisation
- MCP and A2A patterns, permissions, approvals and audit for assistants that act
- Responsible AI and AI governance (EU AI Act awareness a plus)
- Stakeholder engagement, design thinking and Lean process methods, and business value creation
- Coaching and learning agility
- English
Skills Desired
Artificial Intelligence (AI), Biostatistics, Business Value Creation, Change Management, Curious Mindset, Data Governance, Data Literacy, Data Quality, Data Science, Data Visualization, Deep Learning, Generative AI, Graph Algorithms, Learning Agility, Machine Learning (ML), Machine Learning Algorithms, Neuro-Linguistic Programming (NLP), Organizational Awareness, Pandas Python Library, Python (Programming Language), R Programming, Stakeholder Engagement, Statistical Analysis, Structured Query Language (SQL), Time Series AnalysisNovartis Dublin, Dublin, IRL Office
203 Merrion Rd, Dublin, Ireland, D04 NN12
Similar Jobs
Biotech • Pharmaceutical
Build and scale language-based skills, workflows, and agents for enterprise AI assistants supporting drug development program, portfolio, governance, and planning processes. Design trusted knowledge layers, MCP connectors, A2A integrations, evaluation frameworks, and guardrails for AI systems that draft or update business records. Partner with process owners, quality, compliance, and technology teams to deploy governed solutions, measure impact, maintain system registries, and coach early-career scientists.
Top Skills:
Agent-To-Agent (A2A) IntegrationAPIsAws KiroClaude CodeClaude CoworkGithub CopilotMicrosoft Copilot CoworkMicrosoft TeamsModel Context Protocol (Mcp)PandasPythonRSharepointSQL
Blockchain • Fintech • Payments • Consulting • Cryptocurrency • Cybersecurity • Quantum Computing
Oversee IT service management processes for Mastercard network operations, including incident, problem, and change management. The role evaluates and audits network changes, conducts root cause analysis, tracks remediation, prepares executive post-incident reviews, reports on performance indicators, identifies process improvements, and performs network integrity and performance analysis. The engineer also coaches team members and ensures adherence to ITIL, ITSM, security, and change-management requirements.
Top Skills:
ItilItsmNetwork Routing And SwitchingRemedy
Blockchain • Fintech • Payments • Consulting • Cryptocurrency • Cybersecurity • Quantum Computing
Oversee incident, problem, and change management for Mastercard network programs. Ensure ITSM policy adherence, audit tickets, conduct root cause analysis, track remediation, evaluate network changes, and report KPIs to leadership. Perform network analysis, identify process gaps, support post-incident reviews, and coach team members. The role requires advanced ITIL and ITSM knowledge, network routing and switching expertise, reporting skills, and strong communication.
Top Skills:
ItilItsmNetwork RoutingNetwork SwitchingRemedy
What you need to know about the Dublin Tech Scene
From Bono and Oscar Wilde to today's tech leaders, Dublin has always attracted trailblazers, with more than 70,000 people working in the city's expanding digital sector. Continuing its legacy of drawing pioneers, the city is advancing rapidly. Ireland is now ranked as one of the top tech clusters in the region and the number one destination for digital companies, with the highest hiring intention of any region across all sectors.

