• Lead teams building and delivering federated large molecule AI systems, staying hands-on across antibody modeling, co-folding, binder prediction, and developability • Build and implement ML applications large biomolecular foundation models such as OpenFold, Boltz-2 and ESM • Own delivery of these against committed milestones and ensure high-quality model releases ship on time • Translate ambiguous scientific and technical goals into clear plans, priorities, workstreams, and decisions • Guide evaluation decisions and build on them to deliver results packages to external stakeholders • Surface risks, blockers, bugs, timeline changes, and technical trade-offs early, with clear recommendations • Align consortium members on objectives, evaluation criteria, data requirements, timelines, and delivery expectations • Work with product, engineering, research, and leadership to ensure application requirements shape the model roadmap.

• Lead the strategic design and governance of the technical platform (IDP). • Conduct an initial diagnostic and immersion (assessment) lasting 2 to 4 weeks. • Develop the platform blueprint and the strategic roadmap for architectural evolution. • Establish technical governance for technology choices, microservices standardization, SDKs, and the use of message queues. • Drive platformization to provide accelerators that support product teams. • Act as a technical enabler, empowering product teams and ensuring integration with existing corporate solutions.

• Own the New Relic query language stack including grammar parsing, compilation, and processing. • Proactively participate in cross-functional committees to move the query language forward, ranging from collaborations with AI, Visualizations, and Data Processing teams. • Build and maintain scalable distributed Java services and Petabyte-scale Infrastructure. • Investigate and resolve critical performance, availability, and resiliency issues and risks in a multi-region, multi-cloud, multi-tenant distributed database. • Working in an agile environment with a DevOps approach — the team builds and maintains their own software, including taking turns with being on-call.

• Design realistic terminal-based benchmark tasks for AI evaluation systems • Create technically deep debugging and investigation scenarios • Develop task specifications involving infrastructure, workflows, pipelines, or operational failures • Write clear solution approaches and deterministic evaluation criteria • Identify realistic edge cases, failure modes, and system constraints • Design multi-step reasoning challenges across complex technical environments • Contribute expertise across one or more engineering or operational domains • Review and refine benchmark quality, difficulty, and validation logic • Collaborate with reviewers and researchers on AI evaluation workflows