Staff Python Engineer (Modeling & Simulation)
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). Do NOT repeat the job title as a heading (the page already shows it) and do NOT put Job ID / requisition numbers as headings — fold minor metadata into a short
or drop it. Preserve ALL substantive information; do NOT invent or summarize away detail. Remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. We need to parse the posting and extract relevant content. Let's read the posting: - Intro: "About Code Metal Code Metal is the leader in automated software engineering you can trust. As AI writes more of the world's code, the bottleneck in software has shifted from writing code to verifying it works, and AI cannot verify its own work with certainty. Code Metal takes a fundamentally different approach: constrain AI to what it does reliably, verify every step independently of the model using formal methods, and keep engineers in the loop on the decisions that matter. The result isn't code that probably works — it's code that is provably correct, with auditable proof. Customers including the U.S. Air Force, L3Harris, RTX, and Toshiba use Code Metal to modernize legacy code, optimize performance on real hardware, and move prototypes to production, fast. Founded in 2023 with offices in Boston and San Francisco, Code Metal is funded by Accel, Salesforce Ventures, B Capital, Smith Point Capital, J2 Ventures, Shield Capital, Overmatch, RTX, and others. Learn more at codemetal.ai. Our Modeling & Simulation team is building the next-generation wargaming and decision-support platform that helps the DoW make multi-billion-dollar force-design decisions before those decisions are made in the real world. The team spans simulation and physics, backend and data systems, frontend and geospatial visualization, and AI systems, working together to turn operational questions into extensible, mission- and campaign-level simulations that government users can trust. In this role, you will help build the Python services, pipelines, and tooling that drive the core wargaming simulation. You will design backend services and APIs that interface with the frontend, integrate with multiple simulators, manage the data, and expose results to analysts, model developers, and government stakeholders. Scope of ownership, architectural authority, and mentorship responsibility scale with level — see “Level Expectations by Track” below. You'll develop the backend infrastructure that interfaces with agentic AI and machine learning pipelines to support platform, sensor, behavior, and decision models used across the simulation, while building extensible, well-tested foundations for the broader wargaming platform. You'll help design scenario-generation, Monte Carlo, sensitivity-analysis, and campaign-evaluation workflows, and build the distributed, cloud-scale infrastructure that lets simulations run across developer workstations, on-premises infrastructure, and cloud compute while preserving reproducibility and model provenance. Strong command of cloud services and distributed architectures is essential." Then heading "About The Role" with bullet list of responsibilities. Then "Required Qualifications:" list. Then "Preferred Qualifications:" list. Then "Staff Level Expectations" with subpoints: Years of Experience: 7+ etc. Then "Benefits" list: Pay depends on experience, but we strive to be at the upper end of the salary range; Health care plan with 100% premium coverage, including medical, dental, and vision; 401k with 5% matching; Paid Time Off (uncapped vacation, plus sick and public holidays); Flexible hybrid or remote work arrangement; Relocation assistance for qualifying employees. Then "Wage Transparency - The salary range for this role is not a guarantee of compensation or salary, as the final offer amount may vary based on factors including, but not limited to, individual proficiency, skills, experience, and location." That's about Pay. Then "We are an equal opportunity employer. US Citizenship may be required for certain project assignments involving security clearance. Pursuant to the San Francisco Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records." That's EEO boilerplate, remove. We need to produce sections: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We need to decide which sections have content. - About the role: The posting includes "About The Role" heading with bullet list of responsibilities. So we can put that under
About the role
and then maybe asummarizing? Actually we need to preserve substantive information; we can put the bullet list as
- ... under that heading. The "About The Role" paragraph before bullet list is also part of about the role. So we can include that as
then
- .
- Responsibilities: The bullet list under "About The Role" actually are responsibilities. Could we separate? The instructions: Use headings for sections like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We could put responsibilities under Responsibilities heading. But the posting has "About The Role" then bullet list of responsibilities. We could treat "About the role" as a short intro paragraph, and then responsibilities as separate section. However we must not repeat content. We could put the intro paragraph under About the role, and the bullet list under Responsibilities. That seems logical.
- Requirements: The posting has "Required Qualifications:" which are requirements. Could map to Requirements heading.
- Qualifications: Could be "Preferred Qualifications:" maybe under Qualifications heading? Or we could have both Required and Preferred under Qualifications? The instruction says use headings for sections like Requirements, Qualifications, Skills. We could have Requirements for required qualifications, Qualifications for preferred qualifications, Skills maybe for specific technical skills? But we have many skill-like items in required/preferred. Could also create Skills section for things like "Professional experience with collaborative, enterprise-level software development in Python", "Experience building and delivering robust software using strong SDLC practices", "Familiarity with machine learning tools and frameworks", "Expertise building scalable APIs (REST, GraphQL, gRPC)", "Hands-on experience with Docker and containerized application development", "Eligible to obtain and maintain an active U.S. Top Secret security clearance." Those are qualifications/requirements. Could treat them as Requirements. Preferred qualifications could be separate Qualifications.
Skills: Could extract specific technical skills like "Python", "REST, GraphQL, gRPC", "Docker", "cloud services (AWS, GCP, Azure)", "agentic AI frameworks", "code analysis/static analysis", "HLA, DIS, OneSAF, JSAF, NGTS, STK", etc. But we risk duplication. Perhaps better to not create Skills section if content overlaps heavily; we can put skills under Requirements/Qualifications. The instruction: "Prefer a few substantive sections over many thin ones." So we might combine.
We need to include Benefits, Pay, Schedule sections only if posting has real specific content.
Benefits: Yes we have list.
Pay: The posting includes "Pay depends on experience, but we strive to be at the upper end of the salary range" and also wage transparency note. That's specific enough for Pay section.
Schedule: Not explicitly mentioned; there is "Flexible hybrid or remote work arrangement" which is about work arrangement, not schedule. No explicit schedule like hours. So we should not create Schedule section.
Thus sections: About the role, Responsibilities, Requirements, Qualifications, Benefits, Pay.
We need to ensure we don't include filler like "commensurate with experience". The Pay section includes "Pay depends on experience, but we strive to be at the upper end of the salary range". That's specific enough.
We must not include boilerplate like EEO, equal opportunity, etc.
Now we need to extract content.
Let's parse:
About Code Metal description: Could be part of About the role? The instructions: "Do NOT repeat the job title as a heading (the page already shows it)". The About Code Metal is company overview, not role-specific. Might be considered part of About the role? Usually "About the role" includes role description, not company. But we could include a brief company overview under About the role as context. However the instruction says preserve ALL substantive information; we should not omit company description if it's substantive. But the heading "About the role" is for role-specific info. The company description could be placed under a separate heading like "About Code Metal" but that's not in allowed headings list. The allowed headings are only those listed. We could incorporate company description into About the role paragraph as introductory context. That seems acceptable.
Thus About the role section: include company overview paragraph and then maybe a short description of the role (the paragraph before bullet list). Then responsibilities under Responsibilities heading.
Let's extract:
Company overview: "About Code Metal Code Metal is the leader in automated software engineering you can trust. As AI writes more of the world's code, the bottleneck in software has shifted from writing code to verifying it works, and AI cannot verify its own work with certainty. Code Metal takes a fundamentally different approach: constrain AI to what it does reliably, verify every step independently of the model using formal methods, and keep engineers in the loop on the decisions that matter. The result isn't code that probably works — it's code that is provably correct, with auditable proof. Customers including the U.S. Air Force, L3Harris, RTX, and Toshiba use Code Metal to modernize legacy code, optimize performance on real hardware, and move prototypes to production, fast. Founded in 2023 with offices in Boston and San Francisco, Code Metal is funded by Accel, Salesforce Ventures, B Capital, Smith Point Capital, J2 Ventures, Shield Capital, Overmatch, RTX, and others. Learn more at codemetal.ai. Our Modeling & Simulation team is building the next-generation wargaming and decision-support platform that helps the DoW make multi-billion-dollar force-design decisions before those decisions are made in the real world. The team spans simulation and physics, backend and data systems, frontend and geospatial visualization, and AI systems, working together to turn operational questions into extensible, mission- and campaign-level simulations that government users can trust."
Then role-specific paragraph: "In this role, you will help build the Python services, pipelines, and tooling that drive the core wargaming simulation. You will design backend services and APIs that interface with the frontend, integrate with multiple simulators, manage the data, and expose results to analysts, model developers, and government stakeholders. Scope of ownership, architectural authority, and mentorship responsibility scale with level — see “Level Expectations by Track” below. You'll develop the backend infrastructure that interfaces with agentic AI and machine learning pipelines to support platform, sensor, behavior, and decision models used across the simulation, while building extensible, well-tested foundations for the broader wargaming platform. You'll help design scenario-generation, Monte Carlo, sensitivity-analysis, and campaign-evaluation workflows, and build the distributed, cloud-scale infrastructure that lets simulations run across developer workstations, on-premises infrastructure, and cloud compute while preserving reproducibility and model provenance. Strong command of cloud services and distributed architectures is essential."
We could combine these into About the role paragraph(s). Then Responsibilities bullet list:
- Design and implement backend services and APIs that orchestrate mission- and campaign-level simulation runs, collect their outputs, and expose results to analysts and government stakeholders.
- Build scenario-generation, operational and mission planning workflows, and key services for Monte-Carlo based sensitivity-analysis for our wargaming and decision-support platform.
- Build distributed, cloud-scale infrastructure that scales simulations across developer workstations, on-premises infrastructure, and cloud compute while preserving reproducibility and model provenance.
- Build data ingestion, normalization, and analysis pipelines that turn raw simulation output into decision-ready insight for defense users.
- Build