Research Scientist, Agentic Workflows

We need to output HTML fragment with sections: headings

for sections like About the role, Responsibilities, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We must include only sections that have real specific content. We must not repeat job title. No Job ID heading. We must preserve all substantive info, remove boilerplate, navigation, legal, EEO, scam warning, duplicated lines, application instructions. Also remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. We need to parse the posting. Key sections: Overview: description of role, mission, group, etc. Could be "About the role" or maybe "Overview". The instruction says use

for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we can map content to these headings. We have: - Overview: description of role, mission, group, etc. Could be "About the role". - Major Duties/Responsibilities: list of duties (Provenance and Runtime Data Capture Systems, Multi-Institutional Project and Technical Leadership, Solutions Architecture for Facility Platforms, Agentic Workflow Design and Autonomous Control Systems, Open-Source Software Leadership, Research Collaboration and Mentorship, Scientific Domain Support, Research and Publication). That's responsibilities. - Basic Qualifications: list of qualifications (PhD, experience, etc.) Could be "Requirements" or "Qualifications". The instruction includes both Requirements and Qualifications as possible headings. We need to decide. Usually "Requirements" for basic qualifications, "Preferred Qualifications" for preferred. Could have "Requirements" for basic, "Qualifications" for preferred? Or we could combine. But we should not create thin sections. We have both basic and preferred qualifications; we could have a "Requirements" section for basic, and a "Qualifications" section for preferred. Or we could have "Skills" for technical skills. But we have specific skills: Python, Bash, C/C++, Linux HPC, SLURM/PBS, provenance models, etc. Could be under Skills. We also have Remote/Hybrid Eligibility, Special Requirements (security), Why Join Us, About ORNL, benefits list, etc. Benefits: they list many benefits. So we can have a Benefits section. Pay: not mentioned explicitly. No salary info. So we should not create Pay section. Schedule: not mentioned explicitly (though hybrid eligibility mentions flexible work). Not a specific schedule. So we should not create Schedule section unless explicit. We must not create sections with filler like "commensurate with experience". So we skip Pay and Schedule. We need to include Benefits section because they list benefits. We need to include maybe "About the role" (overview). Responsibilities (major duties). Requirements (basic qualifications). Qualifications (preferred qualifications). Skills (maybe list of technical skills). Benefits (list). Possibly also "Remote/Hybrid Eligibility" could be part of Benefits or maybe a separate section like "Work Arrangement". But not in allowed headings list. The allowed headings are only those listed; we should not create other headings. So we should fold remote/hybrid info into Benefits or maybe into About the role? Probably Benefits. Special Requirements (security) could be part of Requirements? It's a requirement for employment. Could be included in Requirements. Why Join Us and About ORNL could be part of About the role or maybe separate but not in allowed headings. Could fold into About the role. We must preserve all substantive information. So we need to include details from those sections somewhere. Let's plan sections:

About the role

: include overview description (ORNL seeking Research Scientist, agentic workflow orchestration, cross-facility integration, group, mission, etc.) plus maybe Why Join Us and About ORNL? But we need to keep it concise but preserve all substantive info. Could be long but okay.

Responsibilities

: list of duties as

• each duty with its subpoints? The duties have sub-bullets. We need to preserve all detail. Could nest
  inside
  • ? The instruction says use
    • for any list of duties/requirements/benefits. It doesn't forbid nested lists. So we can have top-level
      for each duty, and inside each
      • we can have a
        for subpoints. That preserves detail.

        Requirements

        : basic qualifications plus special requirements (security, credentialing). Could also include remote/hybrid eligibility? Might be better to put remote/hybrid in Benefits? But we can include in Requirements as a note about work arrangement. However remote/hybrid eligibility is not a qualification but a condition. Could be placed in Benefits? Might be better to include in About the role? But we need to preserve it. Perhaps we can include a short paragraph under About the role about hybrid eligibility. Or we could create a separate section "Work Arrangement" but not allowed. So we fold into Benefits? Benefits section is for benefits like medical, retirement, etc. Remote/hybrid eligibility is more about work arrangement. Could be placed in About the role as a note. We'll include remote/hybrid eligibility in About the role paragraph.

        Qualifications

        : preferred qualifications.

        Skills

        : technical skills: Python, Bash, C/C++, Linux HPC, SLURM/PBS, provenance models (W3C PROV), agentic workflows, open-source software leadership, CI/CD, etc. Could also include communication skills. But communication skills already in Requirements. We'll list technical skills.

        Benefits

        : list of benefits as provided. We must not include boilerplate like "This position will remain open for a minimum of 5 days..." etc. That's application instructions; remove. Also remove "We accept Word (.doc, .docx)...", "Resumes from third party vendors will not be accepted", "If you have trouble applying...", "ORNL is an equal opportunity employer...", "UT-Battelle is an E-Verify employer." Remove. Also remove "Special Requirements: Security, Credentialing, and Eligibility Requirements:" we will incorporate the content but not the heading. We must not repeat job title. Now craft HTML. We'll start with

        About the role

        ...

        Let's write About the role paragraph: "Oak Ridge National Laboratory (ORNL) is seeking a Research Scientist to work on 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). The position is within the Workflows and Ecosystem Services (WES) Group at the National Center for Computational Sciences (NCCS). You will design and deploy agentic workflows and frameworks that bridge leadership computing resources, instruments, and cloud platforms, collaborating with scientists, facility operators, and DOE laboratory partners to lower barriers to scalable, automated scientific computing. The WES Group focuses on 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. NCCS provides state-of-the-art computational and data science infrastructure and hosts the OLCF, home to Frontier, the first exascale supercomputer. The role offers a hybrid (onsite + remote) work arrangement within approved U.S. states, subject to business needs and approvals." We could also include Why Join Us and About ORNL details: "Work on the world’s most powerful supercomputers, including Frontier... Drive cross-facility research infrastructure... Collaborate with diverse teams... Grow your career in a mission-driven, innovation-focused environment... Enjoy life in East Tennessee..." and ORNL overview. Let's incorporate to preserve all substantive info. Thus About the role paragraph will be long but okay. Now Responsibilities: list each major duty with subpoints. We'll create
        with
        • for each duty. Inside each
        • , we can have a
          for subpoints. Duty 1: Provenance and Runtime Data Capture Systems: Lead the research and development of runtime data integration and provenance capture systems (e.g., Flowcept) that instrument distributed scientific workflows, ML training pipelines, and agentic systems. Design low-overhead instrumentation and adapters for common execution frameworks, define provenance data models aligned with community standards (e.g., W3C PROV), and build the query, storage, and streaming layers (e.g., message brokers, document and time-series stores) required to make workflow telemetry usable at scale. Drive the technical roadmap, release process, and architecture of the software. Duty 2: Multi-Institutional Project and Technical Leadership: Serve as ORNL's technical lead for cross-facility initiatives (e.g., AmSC, Genesis Mission) that build interoperable provenance and workflow-data capabilities spanning leadership computing, experimental facilities, and cloud platforms. Design services that track data lineage, model artifacts, and computational campaigns across the DOE complex, and coordinate with partner laboratories to align schemas, APIs, and metadata standards so that provenance is portable between facilities. Define technical scope, coordinate multi-institutional development teams, track milestones and deliverables, and represent ORNL in project-level technical planning. Contribute to proposals and reports that sustain and grow the portfolio. Duty 3: Solutions Architecture for Facility Platforms: Serve as solutions architect for OLCF platform efforts (e.g., OPAL), translating scientific and programmatic requirements into deployable system designs. Evaluate architectural trade-offs across orchestration, data management, storage, and security; produce reference architectures and integration patterns; and work with facility operations staff to move designs from prototype into production. Duty 4: Agentic Workflow Design and Autonomous Control Systems: Design and implement agentic workflow architectures that enable autonomous, closed-loop scientific experimentation across HPC and instrument facilities. 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 decisions and tool use. Apply these patterns to use cases such as autonomous materials discovery, self-steering simulations, and adaptive experimental campaigns. Duty 5: Open-Source Software Leadership: Own the technical direction and health of open-source research software: code review, CI/CD, testing, packaging, documentation, and release management. Grow and support an external contributor and user community, respond to issues, and ensure software is deployable beyond ORNL. Duty 6: Research Collaboration and Mentorship: Establish and sustain research collaborations with universities, national laboratories, and international partners. Define joint research directions, co-supervise students, interns, and postdocs, and convert collaborative work into shared software and publications. Duty 7: Scientific Domain Support: Collaborate with domain scientists in areas such as materials science, climate science, and autonomous experimentation to translate research objectives into scalable, automated workflow and data-capture solutions. Provide documentation, training, and direct user support. Duty 8: Research and Publication: Conduct original research on provenance, workflow systems, orchestration, and data management for AI-driven science. Publish in high-impact peer-reviewed venues and present at major conferences (e.g., SC, HPDC, IPDPS, eScience). Now Requirements (basic qualifications) plus special requirements (security). We'll list as
          • items. Basic qualifications: - Ph.D. in Computer Science, Computer Engineering, or a closely related field. - At least 3 years of experience designing or operating distributed systems, provenance frameworks, or workflow orchestration frameworks. - At least 2 years of experience designing agentic workflows. - At least 2 years of programming experience in Python, with working familiarity in Bash and/or a compiled language (C/C++ or similar). - Experience with Linux-based HPC environments and familiarity with job scheduling systems (e.g., SLURM or PBS). - Strong verbal and written communication skills, with the ability to collaborate across technical and scientific teams. Special requirements (security