Senior Applied Scientist, Leo Security

We need to output HTML fragment with sections: headings

for sections like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Only include sections that have real content. We need to parse the job posting. Key parts: - Description: about the role (Amazon Leo constellation, Applied Scientist founding scientist, etc). This is "About the role" content. - Export Control Requirement: mention US citizen etc. This could be part of Requirements or Qualifications? It's a requirement. Could be placed under Requirements. - Key job responsibilities: list bullet points. - A day in the life: maybe part of About the role? Could be separate but not required heading. We can include under About the role or Responsibilities? Probably part of About the role. - About The Team: could be About the role or separate section? Could be "About the Team". Not in list of allowed headings but we can use "About the role" maybe includes team description. However we have allowed headings: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We should map content accordingly. - Inclusive Team Culture, Training & Career Growth, Work/Life Balance: these could be under Benefits? Or maybe under Skills? Not exactly. They are cultural aspects. Could be placed under Benefits? But they are not benefits like health insurance. Could be omitted? The instruction: include a section ONLY when posting has real, specific content for it. We have content for Inclusive Team Culture, Training & Career Growth, Work/Life Balance. But there is no heading for those in allowed list. We could fold them into a short

under Benefits? Not ideal. Perhaps we can create a section "About the role" that includes team culture etc. Or we could create a "Skills" section for qualifications? Actually Skills could include technical skills. But the cultural aspects are not skills. Given constraints, we should only use allowed headings. So we need to map content to those headings. If content doesn't fit, we can either omit or fold into existing sections like About the role or Responsibilities. Thus: - About the role: include description of role, day in the life, about the team, inclusive culture, training, work-life balance maybe. - Responsibilities: list key job responsibilities bullet points. - Requirements: basic qualifications plus export control requirement. - Qualifications: preferred qualifications. - Skills: maybe list specific technical skills? Could combine with qualifications? But we have both Requirements and Qualifications sections. Could treat Requirements as basic qualifications, Qualifications as preferred qualifications. Skills could be something like programming languages, graph algorithms etc. But those are already in qualifications. Might be redundant. We could omit Skills if no distinct content. - Benefits: we have benefits description: health insurance, 401(k) matching, paid time off, parental leave, etc. Also mention sign-on payments and RSUs. So we can create Benefits section. - Pay: we have salary ranges for locations. So we can include Pay section. - Schedule: not mentioned; flexible work hours arrangements mentioned under Work/Life Balance. Could be considered schedule. But we have no explicit schedule. Could omit Schedule. Thus produce HTML:

About the role

... combined description ...

Responsibilities

• ... each responsibility ...

Requirements

• ... basic qualifications + export control ...

Qualifications

• ... preferred qualifications ...

Benefits

• ... benefits ...

Pay

Salary ranges: ...

We must not repeat job title as heading. No Job ID. We must preserve all substantive information. Must not invent or summarize away detail. Must not include boilerplate like EEO etc. Remove those. We need to include all bullet points from responsibilities, basic qualifications, preferred qualifications, benefits, pay ranges. Let's extract. Responsibilities bullet points (from "Key job responsibilities"): - Design and implement scalable, production-grade neurosymbolic systems that integrate symbolic reasoning over graph-based knowledge representations with LLM agents to deliver reliable, verifiable security outcomes. - Design and run reinforcement learning and fine-tuning pipelines (GRPO, PPO, DPO) to optimize language models for security reasoning, triage, and detection-authoring tasks. - Build behavioral and statistical models that detect threat actor behavior, and design the evaluation frameworks that measure model performance against that behavior before trusting a model in production. - Design and build multi-agent systems that autonomously triage, enrich, and contain security events, including the constrained reasoning, safety guardrails, and validation mechanisms that make automated decisions trustworthy at scale. - Own the end-to-end science lifecycle, from research and experimentation through production deployment, defining the metrics that measure system performance and real-world security impact. - Advance the state of the art through publications at top-tier venues, patents, or open-source contributions, and shape the scientific agenda and research culture from day one. Also "A day in the life" paragraph: we can incorporate into About the role. About the role content: combine description paragraph, day in the life, about the team, inclusive team culture, training & career growth, work/life balance. Let's craft a paragraph that includes all that info without losing detail. Description: "Amazon Leo is a constellation of Low Earth Orbit satellites that will provide low-latency, high-speed broadband network connectivity to unserved and underserved communities around the world. We are looking for an Applied Scientist to be a founding scientist on the Engineering and R&D team within Leo Infrastructure and IP Security. The team defends the manufacturing lines, launch sites, and global ground infrastructure behind the constellation from the most sophisticated threat actors on the planet. These requirements create open scientific problems at the intersection of agentic AI, real-time stream processing, graph-based reasoning, and behavioral analytics. You will build the science behind a neurosymbolic reasoning platform and the models that detect the behavior of sophisticated threat actors. This is an R&D role with a production mandate, where you define the problem rather than solve a pre-scoped one, and every model, detection, and agent workflow you build becomes the system Leo's security teams use to protect the constellation." Day in the life: "You will move between research and production in the same week: framing an ambiguous security problem as a scientific question, prototyping an approach, and partnering with software engineers to ship it as a capability the platform runs continuously. Security engineers on your team translate threat intelligence into the adversary behaviors that matter; you build the models that detect those behaviors and evaluate model performance against them. You will obsess over the two latencies that define the platforms, the time from event to detection and the time from detection to containment action, and design agents and detections that drive both down. You will backtest candidate detections against retained telemetry, review evaluation results before a model or agent capability graduates to automated execution, and deliver scientific artifacts that ship." About The Team: "Leo Infrastructure and IP Security protects the people, facilities, hardware, and supply chain behind a global satellite constellation. The Engineering and R&D team within this organization builds the platforms and tooling the security pillar teams operate on, moving security operations from manual triage to correlation-based detection, automated response, and agentic AI. The team is composed of applied scientists, software engineers, and security engineers working across physical and digital security domains." Inclusive Team Culture: "In Amazon Security, it's in our nature to learn and be curious. Ongoing DEI events and learning experiences inspire us to continue learning and to embrace our uniqueness. Addressing the toughest security challenges requires that we seek out and celebrate a diversity of ideas, perspectives, and voices." Training & Career Growth: "We're continuously raising our performance bar as we strive to become Earth's Best Employer. That's why you'll find endless knowledge-sharing, training, and other career-advancing resources here to help you develop into a better-rounded professional." Work/Life Balance: "We value work-life harmony. Achieving success at work should never come at the expense of sacrifices at home, which is why flexible work hours and arrangements are part of our culture. When we feel supported in the workplace and at home, there's nothing we can't achieve." We can combine these into About the role section as multiple paragraphs. Now Requirements (basic qualifications + export control): Basic Qualifications: - 3+ years of building machine learning models for business application experience - PhD, or Master's degree and 6+ years of applied research experience - Experience programming in Java, C++, Python or related language - Experience with neural deep learning methods and machine learning - Experience with graph algorithms, knowledge graphs, unsupervised learning (clustering, dimensionality reduction, anomaly detection), NLP, and embedding-based retrieval - Experience designing evaluation frameworks for AI systems where ground truth requires human judgment, including staged rollouts, A/B testing, and expert feedback loops Export Control Requirement: "Due to applicable export control laws and regulations, candidates must be a U.S. citizen or national, U.S. permanent resident (i.e., current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum." We can include that as a bullet. Qualifications (preferred): - Experience with modeling tools such as R, scikit-learn, Spark MLLib, MxNet, Tensorflow, numpy, scipy etc. - Experience in building quantitative solutions as a scientist or science manager - Experience in one or more of the following domains: access-control system and methodology, network security, application- and system-development security, security architecture and models, cryptography, and operations security - Experience with terabyte-scale stream processing and real-time correlation of heterogeneous event sources - Experience with cost and latency optimization for LLM-based systems (token reduction, schema optimization, deterministic offloading) - Publications in applied ML, graph analytics, agentic AI, or security analytics Benefits: - Amazon package includes sign-on payments and restricted stock units (RSUs). - Comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage) - 401(k) matching - Paid time off - Parental leave - Learn more about benefits at https://amazon.jobs/en/benefits (but we may drop URL as it's maybe boilerplate? It's not EEO; it's a link to benefits. Might be okay to keep but it's a link. The instruction says remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. This is not those. It's a benefits link. Could keep but it's a URL; maybe okay. However we might drop as it's not substantive content? It's a reference. I'd keep it as part of benefits description. Pay: - Base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. - USA, VA, Arlington - 167,100.00 - 226,100.00 USD annually - USA, VA, Herndon - 167,100.00 - 226,100.00 USD annually - USA, WA, BELLEVUE - 167,100.00 - 226,100.00 USD annually We should not repeat sign-on payments and RSUs in both Benefits and Pay? It's okay but we might duplicate. The instruction: Preserve ALL substantive information; do NOT invent or summarize away detail. Duplication is okay if it's in original. But we might avoid duplication by mentioning sign-on payments and RSUs only once, maybe in Benefits. In Pay we can mention base salary range and that final compensation based on experience etc. We can keep sign-on payments and RSUs in