Research Associate, Agentic Workflows

Requisition  Overview:
Oak Ridge National Laboratory (ORNL) is seeking a Research Scientist to support agentic workflow orchestration and cross-facility integration in support of the Genesis Mission, the American Science Cloud, and the Oak Ridge Leadership Computing Facility (OLCF). Working within the Workflows and Ecosystem Services (WES) Group at the National Center for Computational Sciences (NCCS), you will help design, implement, and deploy agentic workflows and frameworks that bridge leadership computing resources, instruments, and cloud platforms, working under the guidance of senior technical staff.

You will collaborate with scientists, facility operators, and DOE laboratory partners to lower barriers to scalable, automated scientific computing.

WES designs and implements workflow, data, and ecosystem technologies that enable reliable, automated execution of scientific applications across heterogeneous, geographically distributed computing environments, integrating compute, storage, networking, and visualization resources into cohesive, end-to-end systems.

The WES Group sits within the Advanced Technologies section of the National Center for Computational Sciences (NCCS), a division of the Computing and Computational Sciences Directorate (CCSD) S provides state-of-the-art computational and data science infrastructure for technical and scientific professionals and hosts the Oak Ridge Leadership Computing Facility (OLCF), a DOE Office of Science User Facility that is home to Frontier, the first supercomputer to break the exascale barrier.

NCCS staff work at the forefront of leadership computing, enabling scientific discovery for researchers across government, academia, and industry.

Major Duties/Responsibilities:

Provenance and Runtime Data Capture Systems:
Contribute to the development of runtime data integration and provenance capture systems (e.g., Flowcept) that instrument distributed scientific workflows, ML training pipelines, and agentic systems. Help implement low-overhead instrumentation and adapters for common execution frameworks, apply provenance data models aligned with community standards (e.g., W3C PROV), and support the query, storage, and streaming layers (e.g., message brokers, document and time-series stores) needed to make workflow telemetry usable ss-Facility Integration Support:
Support ORNL's participation in cross-facility initiatives (e.g., AmSC, Genesis Mission) that build interoperable provenance and workflow-data capabilities spanning leadership computing, experimental facilities, and cloud platforms. Help build services that track data lineage, model artifacts, and computational campaigns across the DOE complex, and assist in coordinating with partner laboratories to align schemas, APIs, and metadata standards so that provenance is portable between facilities.

Track milestones and deliverables and contribute to proposals and reports that sustain the portfolio.

Platform Integration Support:
Support OLCF platform efforts (e.g., OPAL) by helping translate scientific and programmatic requirements into deployable system designs. Assist in evaluating architectural trade-offs across orchestration, data management, storage, and security, and work with senior staff and facility operations to help move designs from prototype toward production.

Agentic Workflow Design and Autonomous Control Systems:
Implement components of agentic workflow architectures that enable autonomous, closed-loop scientific experimentation across HPC and instrument facilities. Help integrate agentic frameworks with provenance and orchestration layers so that AI agents can plan, execute, monitor, and adapt multi-step workflows while producing auditable, reproducible records of their…