2027 Applied Science Internship - Automated Reasoning - United States, PhD Student Science Recruiting, Automated Reasoning
headings and - for lists,
for prose.
We need to preserve all substantive info; not invent.
Let's craft.
About the role: combine the description paragraphs into maybe two
but we can keep as one
. Ensure we keep all details: mention Automated Reasoning and Formal Verification research horizon, shape future of cloud computing, graduate student passionate, join team, revolutionize cloud computing, tools called billions times daily, powering backbone, changing way computer systems developed, raising bar for security, durability, availability, quality, Applied Scientists develop formal methods, automated reasoning, neurosymbolic approaches to ensure security, reliability, correctness of Amazon and AWS services and customer applications. Application areas span cloud infrastructure verification, cryptographic assurance, AI safety, formal guarantees for generative AI systems. Methods range from interactive theorem proving and constraint solving to neuro-inspired proof search. As an Applied Science Intern, you will work alongside scientists and contribute to projects. From distributed proof search and SAT/SMT solvers to program analysis, synthesis, verification, you will tackle complex challenges at intersection of theory and practice. Amazon has positions available for Automated Reasoning Applied Science Internships in, but not limited to, Arlington, VA; Boston, MA; New York, NY; Portland, OR; Santa Clara, CA; Seattle, WA; Austin, TX; Cambridge, UK.
That's a lot; we need to preserve all.
We'll put that in a
.
Responsibilities: list items:
- Contribute to the design and implementation of algorithms and formal methods for automated reasoning, including constraint solving, model checking, static analysis, theorem proving, and program synthesis, within a guided research framework.
- Explore and apply generative AI and machine learning techniques to enhance automated reasoning, including learning-based heuristics for search, neural approaches to symbolic reasoning, and methods for verifying the correctness of AI-generated code.
- Contribute to automated reasoning techniques for generative AI and agentic coding systems, including methods that apply formal guarantees to large language model outputs.
- Contribute to the scientific community through publications at peer-reviewed conferences and journals.
- Leverage AI-powered tools where applicable to accelerate research, experimentation, and prototyping.
- Critically review and validate outputs from AI tools and automated systems.
- The ideal intern must have the ability to communicate research findings clearly to diverse audiences.
Also maybe include "We are particularly interested in candidates with expertise in: Theorem Proving, Boolean Satisfiability Solvers, Bounded Model Checking, Deductive Verification, Programming/Scripting Languages, Abstract Interpretation, Automated Reasoning, Static/Program Analysis, Program Synthesis." That could be under Skills.
We'll keep responsibilities as above.
Requirements (Basic Qualifications):
- Are enrolled in a PhD
- Can relocate to where the internship is based
- Work 40 hours/week minimum and commit to 12 week internship minimum
- Experience programming in Python, and where applicable, C++, Haskell, or Lean
- Experience in one or more of the following: mathematical logic, formal verification, satisfiability solving (SAT/SMT), mechanical theorem proving, model checking, or program analysis
- Demonstrated science depth in a specific research area, evidenced through publications, thesis work, or equivalent contributions
Qualifications (Preferred):
- Experience implementing algorithms using formal methods toolkits (e.g. Lean, Dafny, Isabelle, Rocq, Z3, SAT/SMT solvers, or domain-specific verification frameworks)
- Experience applying formal methods or automated reasoning to real-world software, security, or systems problems
- Experience programming in OCaml, Haskell, Rust, Scala, or a related functional or systems language
- Experience with AI-assisted development tools to accelerate research, coding, or evaluation
Skills: list of expertise:
- Theorem Proving
- Boolean Satisfiability Solvers
- Bounded Model Checking
- Deductive Verification
- Programming/Scripting Languages
- Abstract Interpretation
- Automated Reasoning
- Static/Program Analysis
- Program Synthesis
Benefits:
- Employee Assistance Program (EAP)
- Mental Health Support
- Medical Advice Line
- 401(k) matching
Pay:
- 135,660.00 USD Annually
Schedule:
- Work 40 hours/week minimum and commit to 12 week internship minimum
We must not duplicate schedule from requirements; but it's okay to have both? The requirement includes that; but we can still have schedule section with that info. It's not duplicate if we keep it only in schedule and remove from requirements? But we need to preserve all substantive info; we can keep it in both places? The instruction: "Preserve ALL substantive information; do NOT invent or summarize away detail." It doesn't forbid duplication, but better to avoid duplication? Not required. However we might keep it only in schedule and remove from requirements to avoid redundancy. But the requirement list includes that; if we remove it, we lose that info from requirements section. But we could keep it in both; it's still preserved. Duplication is not prohibited. I'd keep it in both to be safe.
But we might consider moving it to schedule only and note that it's also a requirement; but safer to keep in both.
Now produce HTML.
We'll wrap each section:
About the role
...
Responsibilities
- ...
...
Similarly for Requirements, Qualifications, Skills, Benefits, Pay, Schedule.
For Pay and Schedule, we could use - as well, but they are single items; still okay.
Make sure not to include any extra text.
Let's craft the About the role paragraph precisely.
Original text:
"This role sits within Amazon's Automated Reasoning and Formal Verification research
for prose. We need to preserve all substantive info; not invent. Let's craft. About the role: combine the description paragraphs into maybe two
but we can keep as one
. Ensure we keep all details: mention Automated Reasoning and Formal Verification research horizon, shape future of cloud computing, graduate student passionate, join team, revolutionize cloud computing, tools called billions times daily, powering backbone, changing way computer systems developed, raising bar for security, durability, availability, quality, Applied Scientists develop formal methods, automated reasoning, neurosymbolic approaches to ensure security, reliability, correctness of Amazon and AWS services and customer applications. Application areas span cloud infrastructure verification, cryptographic assurance, AI safety, formal guarantees for generative AI systems. Methods range from interactive theorem proving and constraint solving to neuro-inspired proof search. As an Applied Science Intern, you will work alongside scientists and contribute to projects. From distributed proof search and SAT/SMT solvers to program analysis, synthesis, verification, you will tackle complex challenges at intersection of theory and practice. Amazon has positions available for Automated Reasoning Applied Science Internships in, but not limited to, Arlington, VA; Boston, MA; New York, NY; Portland, OR; Santa Clara, CA; Seattle, WA; Austin, TX; Cambridge, UK. That's a lot; we need to preserve all. We'll put that in a
. Responsibilities: list items: - Contribute to the design and implementation of algorithms and formal methods for automated reasoning, including constraint solving, model checking, static analysis, theorem proving, and program synthesis, within a guided research framework. - Explore and apply generative AI and machine learning techniques to enhance automated reasoning, including learning-based heuristics for search, neural approaches to symbolic reasoning, and methods for verifying the correctness of AI-generated code. - Contribute to automated reasoning techniques for generative AI and agentic coding systems, including methods that apply formal guarantees to large language model outputs. - Contribute to the scientific community through publications at peer-reviewed conferences and journals. - Leverage AI-powered tools where applicable to accelerate research, experimentation, and prototyping. - Critically review and validate outputs from AI tools and automated systems. - The ideal intern must have the ability to communicate research findings clearly to diverse audiences. Also maybe include "We are particularly interested in candidates with expertise in: Theorem Proving, Boolean Satisfiability Solvers, Bounded Model Checking, Deductive Verification, Programming/Scripting Languages, Abstract Interpretation, Automated Reasoning, Static/Program Analysis, Program Synthesis." That could be under Skills. We'll keep responsibilities as above. Requirements (Basic Qualifications): - Are enrolled in a PhD - Can relocate to where the internship is based - Work 40 hours/week minimum and commit to 12 week internship minimum - Experience programming in Python, and where applicable, C++, Haskell, or Lean - Experience in one or more of the following: mathematical logic, formal verification, satisfiability solving (SAT/SMT), mechanical theorem proving, model checking, or program analysis - Demonstrated science depth in a specific research area, evidenced through publications, thesis work, or equivalent contributions Qualifications (Preferred): - Experience implementing algorithms using formal methods toolkits (e.g. Lean, Dafny, Isabelle, Rocq, Z3, SAT/SMT solvers, or domain-specific verification frameworks) - Experience applying formal methods or automated reasoning to real-world software, security, or systems problems - Experience programming in OCaml, Haskell, Rust, Scala, or a related functional or systems language - Experience with AI-assisted development tools to accelerate research, coding, or evaluation Skills: list of expertise: - Theorem Proving - Boolean Satisfiability Solvers - Bounded Model Checking - Deductive Verification - Programming/Scripting Languages - Abstract Interpretation - Automated Reasoning - Static/Program Analysis - Program Synthesis Benefits: - Employee Assistance Program (EAP) - Mental Health Support - Medical Advice Line - 401(k) matching Pay: - 135,660.00 USD Annually Schedule: - Work 40 hours/week minimum and commit to 12 week internship minimum We must not duplicate schedule from requirements; but it's okay to have both? The requirement includes that; but we can still have schedule section with that info. It's not duplicate if we keep it only in schedule and remove from requirements? But we need to preserve all substantive info; we can keep it in both places? The instruction: "Preserve ALL substantive information; do NOT invent or summarize away detail." It doesn't forbid duplication, but better to avoid duplication? Not required. However we might keep it only in schedule and remove from requirements to avoid redundancy. But the requirement list includes that; if we remove it, we lose that info from requirements section. But we could keep it in both; it's still preserved. Duplication is not prohibited. I'd keep it in both to be safe. But we might consider moving it to schedule only and note that it's also a requirement; but safer to keep in both. Now produce HTML. We'll wrap each section:
About the role
...
Responsibilities
- ... ...
- as well, but they are single items; still okay. Make sure not to include any extra text. Let's craft the About the role paragraph precisely. Original text: "This role sits within Amazon's Automated Reasoning and Formal Verification research