Data Scientist - Cleared (Multiple Levels)

We need to output HTML fragment with sections: h3 headings for sections present: About the role? The posting includes responsibilities, qualifications, compensation, maybe benefits? There's a "Total Rewards" section describing benefits. Also "Travel up to 10% within US. Lift up to 30 lbs, walk, bend, drive." That's schedule? Not exactly schedule but physical requirements. There's no explicit schedule. There's compensation details (range). There's benefits described in Total Rewards. There's also "Overview" about company, but that's not required? The instruction: include a section ONLY when posting has real, specific content for it. We can include sections: Responsibilities, Required Qualifications, Desired Qualifications, Compensation, Benefits (Total Rewards), About the company? Could be "About Noblis" maybe as "About the role"? The instruction says use headings like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We need to map content. We have responsibilities (list). We have qualifications: Required Qualifications and Desired Qualifications. Could combine into Requirements/Qualifications. Could have separate sections: Required Qualifications, Desired Qualifications. But we should prefer few substantive sections over many thin ones. Could combine into Qualifications (with sublists). However instruction: use

for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we can choose which headings to include. We need to preserve all substantive info. We have compensation range: $82,500 - $188,725 (posted salary range). Also there are level-specific ranges. We could include Pay section with that range. Benefits: Total Rewards section describes health, life, disability, financial, retirement benefits, paid leave, professional development, tuition assistance, work-life programs. So we can include Benefits. Schedule: Not explicitly given, but there is travel up to 10% within US, lift up to 30 lbs, walk, bend, drive. That's not schedule but physical requirements. Could maybe put under Requirements? There's no explicit schedule/hours. So we should not create Schedule section if no specific content. About the role: Could be the introductory paragraph about Noblis seeking Data Scientists etc. That could be "About the role". We'll include that. Thus sections: About the role (intro paragraph), Responsibilities (list), Qualifications (maybe split Required and Desired? Could combine but we have both). Could do Required Qualifications and Desired Qualifications as separate h3? The allowed headings list includes Requirements, Qualifications, Skills. We could use Qualifications for both required and desired, with subheadings? But we cannot add extra headings beyond h3? We could embed inside? Probably better to have two sections: Required Qualifications and Desired Qualifications, using h3 each. The instruction says use h3 for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It doesn't forbid other headings, but suggests those as examples. Safer to stick to those. Could use Requirements for required qualifications, Qualifications for desired? Or Skills for desired? Let's map: - Responsibilities: h3 - Requirements: h3 (for Required Qualifications) - Qualifications: h3 (for Desired Qualifications) maybe. - Benefits: h3 - Pay: h3 - About the role: h3 We must not repeat job title as heading. We need to output only HTML fragment, no /. Use

• for lists. Use

  for prose. We need to preserve all substantive info: include details about responsibilities list items, required qualifications details (including levels and compensation ranges), desired qualifications list, benefits description, pay range, travel/physical requirements maybe under Requirements? Could add a note under Requirements about travel and physical demands. We must not include boilerplate like EEO, navigation, etc. Remove duplicated lines. Let's extract content. Intro paragraph: "Noblis is seeking Data Scientists at all experience levels with an active TS/SCI with a Polygraph to support mission-critical national security initiatives in Chantilly, Virginia. As a Data Scientist, you will support the intelligence community by developing innovative, data-driven solutions to address mission-critical challenges. You will provide technical expertise to government customers through the development of machine learning, statistical analysis, and data mining solutions. You will collaborate with cross-functional teams including data scientists, software engineers, subject matter experts, and cyber analysts to apply advanced analytics, machine learning, and AI techniques. Additionally, you will contribute to the full model lifecycle, including model development, versioning, deployment, monitoring, and vulnerability identification. Your work will directly contribute to capabilities such as object detection, data triage, search optimization, inference, facial recognition, behavior analysis, and automated decision-making. The ideal candidate will have experience analyzing cyber data and applying data science methodologies to solve complex customer problems, with strong proficiency in Python and experience working with modern AI/ML technologies and cloud-based environments." That's the "About the role". Responsibilities list: after "Key Responsibilities" there is a list of bullet points (starting with Analyze large volumes...). We need to capture each bullet. Let's list them: - Analyze large volumes of structured and unstructured data using open-source datasets, statistical software, cloud services, and AI/ML technologies to identify meaningful patterns, relationships, and insights - Support production AI/ML infrastructure and operations, including platform maintenance, issue triage, troubleshooting, and user support - Support Kubernetes-based platform operations, including the use of management and deployment tools to maintain and optimize AI/ML environments - Work with containerized model-serving environments, contributing to configuration updates, authentication, troubleshooting, and operational support for LLM and multimodal AI capabilities - Explore and model data to identify relevant patterns, trends, relationships, and features of interest - Design, develop, train, evaluate, and refine machine learning models to support mission-focused applications - Collect, curate, clean, transform, and process large-scale structured and unstructured datasets for analytical and machine learning applications - Research, implement, evaluate, and document analytical methodologies, models, and outcomes - Leverage high-performance computing (HPC) resources, including GPU clusters and cloud-based platforms, to support large-scale data processing and model development - Develop data visualizations and analytical products using tools such as Tableau to effectively communicate findings and recommendations to technical and non-technical stakeholders That's responsibilities. Required Qualifications: includes Active TS/SCI with Polygraph, U.S. Citizenship required, then three levels with education/experience and compensation ranges. We need to preserve all details: Level I, Level II, Level III each with education/experience combos and compensation. Also note "Compensation: $82,500 - $128,925" for Level I, etc. Also after Level III: "Travel up to 10% within US.Lift up to 30 lbs, walk, bend, drive." That's physical requirements/travel. We should include that under Requirements maybe as a note. Desired Qualifications: list of items after "Desired Qualifications". Let's capture: - Proficiency in data science tools and technologies such as SQL/PostgreSQL, Apache Spark, and Git - Experience with machine learning, statistical modeling, and/or time-series forecasting - Experience with data visualization tools such as Tableau to communicate findings to technical and non-technical stakeholders - Experience working with cloud platforms such as AWS - Experience working with cyber data, including platforms such as Shodan and Censys - Experience working with open-source and large-scale datasets - Demonstrated ability to clean, transform, manage, and optimize large, complex datasets for analytical and machine learning applications - Fundamental understanding of a range of AI/ML techniques, with the ability to select and apply appropriate methods to address specific problems - Strong written and verbal communication skills, with the ability to effectively communicate technical concepts and analytical findings to diverse audiences - Familiarity with developing, retraining, or using AI and machine learning packages - Knowledge of software and hardware optimization techniques for large-scale data processing - Proficiency in data warehousing, data management, and ETL tools (e.g., Apache NiFi, Pentaho, Kafka) - Experience supporting Kubernetes-based platform operations and containerized model-serving environments - Advanced degree in a data science equivalent field or sub-field Also there is an "Overview" about Noblis company, but that's not required? Could be included under About the role? Already we have intro about role. The Overview about Noblis is more about company; could be included as "About Noblis" but not in allowed headings. Might be considered boilerplate? It's substantive but maybe we can include as a short paragraph under About the role? The instruction: Preserve ALL substantive information; do NOT invent or summarize away detail. So we should include that overview somewhere. Could add a section "About Noblis" but not in allowed headings; but we could still use h3 with that heading? The instruction says use h3 for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It doesn't forbid other headings, but suggests those as examples. Safer to include it under About the role? But About the role already used for intro. Could we have two paragraphs under About the role: first the role description, second the company overview. That would preserve info. Thus About the role section will contain two paragraphs: first the role description, second the company overview (Noblis and subsidiaries etc). We'll need to ensure we don't repeat job title. Now Benefits: Total Rewards section: "At Noblis we recognize and reward your contributions, provide you with growth opportunities, and support your total well-being. Our offerings include health, life, disability, financial, and retirement benefits, as well as paid leave, professional development, tuition assistance, and work-life programs. Our award programs acknowledge employees for exceptional performance and superior demonstration of our service standards. Full-time and part-time employees working at least 20 hours a week on a regular basis are eligible to participate in our benefit programs. Other offerings may be provided for employees not within this category. We encourage you to learn more about our total benefits by visiting the Benefits page on our Careers site." Also earlier: "Compensation at Noblis is determined by various factors..." but that's more about compensation determination; we already have Pay section. We should include Benefits section with that content. Pay section: include the posted salary range: "Posted Salary Range USD $82,500.00 - USD $188,725.00 /Yr." Also we could mention the level-specific ranges but maybe that's too detailed. However we must preserve ALL substantive information; the level-specific ranges are substantive. So we need to include them. Could embed them in Pay section as a list. Thus Pay section: maybe a

  with each level and its range. We also need to include the note about compensation determination factors? That's also substantive but maybe could be omitted? The instruction says preserve ALL substantive information; do NOT invent or summarize away detail. So we should include that paragraph about compensation determination. However that is more general; could be included in Pay section as a paragraph. Thus Pay section will have a paragraph about how compensation is determined, then a list of level-specific ranges, then the posted overall range. Now we need to ensure we don't include boilerplate like EEO, navigation, legal, etc. Remove those. Now produce HTML. Structure:

  About the role

  First paragraph (role description).

  Second paragraph (company overview).

  Responsibilities

  • ...
  ...

  Requirements

  Active Top Secret/SCI (TS/SCI) with Polygraph. U.S. Citizenship is required.

  • Level I: Bachelor's or Master's degree with 1 year