Staff Software Engineer – Agent Engineering

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 specific content. Must not repeat job title as heading. Must not include Job ID etc. Must preserve all substantive info, remove boilerplate, navigation, EEO, etc. Must not include placeholder sections like "commensurate with experience". Must not create Pay/Schedule/Benefits unless posting actually states them. The posting includes salary range: $200,000 - $285,000 per year, also mentions Up to $285,000 base salary for Staff-level candidates, plus equity. So we have Pay info. Also schedule: "Work Arrangement: In-person, 5 days per week" and "full-time". So we have Schedule info. Benefits: mentions equity/ownership, direct access to founders, high technical ownership, etc. Also "Well-funded startup environment", "High-impact customer exposure", "SoHo/NYC office". Those could be considered benefits. We'll create Benefits section with bullet list of those. We need sections: About the role (maybe from "A bit about us:" and "About the Company" and "The Mission"? Actually "About the role" is not explicitly present, but we have "A bit about us:" describing company. Could treat that as About the role? The instruction: use

for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we need to decide which sections have content. We have: - About the role: Could be the description of the role: "The Mission We are seeking a Staff/Senior Software Engineer specializing in Agent Engineering to advance the agent runtime..." plus "What We're Looking For". That seems like role description. We'll put that under About the role. - Responsibilities: There's a "Key Responsibilities" bullet list. - Requirements/Qualifications: There's "What We're Looking For" and "Ideal experience includes:" plus "Nice to Have". Could split into Requirements (must have) and Nice to Have (maybe Skills). But we can combine into Requirements section with bullet list of required experience, and maybe Skills section for nice-to-have? The instruction: prefer few substantive sections over many thin ones. Could combine Requirements and Skills into one? But we have headings list; we can include both if they have content. We have Pay: salary range. Schedule: In-person, 5 days per week, full-time. Benefits: equity, direct access to founders, high technical ownership, etc. We must not include placeholder like "commensurate with experience". The posting includes "based on experience". That's okay. We must not include duplicated lines. Remove boilerplate like EEO, legal, application instructions, etc. Also remove "Want to learn more about this role and Jobot? Click our Jobot logo and follow our LinkedIn page!" repeated. We must output only HTML fragment. Let's extract substantive content: Company description: "We’re an early-stage AI technology company building production-grade agentic systems for complex, high-stakes environments. Our platform combines frontier AI with deep domain expertise to help organizations understand complex information, make better decisions, and take action. Backed by leading institutional investors, our team is building foundational AI infrastructure from the ground up with significant technical ownership and direct collaboration with the founders and CTO." Mission: "We are building a new kind of technology company focused on solving complex, high-impact problems, beginning with the way organizations interact with government. Government influences nearly every consequential market, yet the infrastructure connecting public institutions and private organizations remains fragmented, manual, and difficult to navigate. Our mission is to rebuild that interaction layer. Our core platform provides organizations with the intelligence they need to understand what government is doing, why it matters, and what actions to take next. From that foundation, we design and deploy secure, mission-specific systems for government agencies, enterprises, and institutions operating in complex and highly regulated environments. We combine frontier AI, deep public-sector expertise, and forward-deployed execution. Our team includes experienced leaders and engineers from major technology companies and senior government organizations. We are backed by leading institutional investors and trusted by organizations working on high-stakes challenges across government and industry." The Mission section also includes: "We are seeking a Staff/Senior Software Engineer specializing in Agent Engineering to advance the agent runtime powering our platform's research, analysis, and action capabilities. Our agents must be capable of decomposing open-ended objectives, retrieving trustworthy evidence, safely using tools, coordinating long-running work, and producing high-fidelity outputs that remain traceable to their sources. You will own and improve the systems that make agent behavior reliable in production, including: Execution state and orchestration Tool use and permissions Context and persistent memory Model routing Failure recovery Evaluation and observability Security and operational controls The goal is to enable agents to perform meaningful work over extended periods without losing context, exceeding their authority, silently failing, or producing unsupported conclusions. You will also advance the platform's reasoning and memory layer, enabling agents to accumulate knowledge, recognize changes, resolve contradictions, and maintain direct source context across workflows." That's more role description. What We're Looking For: "We're looking for an experienced engineer who has beyond the prototype stage. You should be comfortable diagnosing nondeterministic failures, establishing clear boundaries between model judgment and deterministic software, and determining when workflows require autonomous execution, human approval, or conventional application logic. Ideal experience includes: Production orchestration of stateful, long-running, and multi-agent workflows Tool and action infrastructure with strong contracts, permissions, and approval boundaries Retrieval, context engineering, evidence management, and persistent agent memory Model-runtime engineering across multiple providers, latency profiles, and deployment environments Evaluation, tracing, security, and operational control of nondeterministic AI systems Designing reliable systems around LLM behavior in production environments" Nice to Have: list. Key Responsibilities: bullet list. Working Here: description of full-time in-person, SoHo NYC office, etc. Compensation: Up to $285,000 base salary for Staff-level candidates, based on experience, plus equity. Also Salary: $200,000 - $285,000 per year. We'll create sections:

About the role

with paragraphs combining company description, mission, role description.

Responsibilities

with

• from Key Responsibilities.

  Requirements

  with
  • from What We're Looking For (ideal experience includes). Could also include "We're looking for an experienced engineer who has beyond the prototype stage..." as a paragraph before list.

    Skills

    maybe for Nice to Have.

    Benefits

    with bullet list: Equity/ownership, Direct access to founders and CTO, High technical ownership, Frontier agentic-AI work, Early-stage impact, Strong founding team, Well-funded startup environment, High-impact customer exposure, SoHo/NYC office.

    Pay

    with paragraph: Salary range $200,000 - $285,000 per year; up to $285,000 base salary for Staff-level candidates based on experience, plus equity.

    Schedule

    with paragraph: Full-time, in-person, 5 days per week in SoHo, New York City office. We must not include placeholder like "not specified". All good. We must not repeat job title as heading. We are not. We must not include Job ID etc. We must not include boilerplate like EEO, legal, application instructions. Remove those. Now produce HTML. Check for any duplicated lines: ensure we don't repeat same bullet. Let's craft. About the role paragraph(s): combine company description and mission and role description. We'll produce maybe two paragraphs. Responsibilities bullet list: from Key Responsibilities: - Own and advance the platform's agent runtime and foundational systems used to build new agent-driven products. - Build infrastructure that allows agents to manage long-running work from initial assignment through completion while keeping activity visible, steerable, and connected to relevant projects, people, evidence, deadlines, and deliverables. - Design and build the tool and action framework agents use to safely interact with internal systems and external services. - Connect agents to retrieval and knowledge systems so reasoning, memory, citations, and generated artifacts remain grounded in authoritative evidence. - Build and improve persistent memory and context-management systems for complex, multi-step agent workflows. - Strengthen evaluation, tracing, simulation, and release processes for agent behavior. - Improve agent quality and reliability while managing latency, inference cost, security, and operational risk. - Diagnose and resolve complex production failures involving nondeterministic AI systems. Requirements bullet list: from Ideal experience includes: - Production orchestration of stateful, long-running, and multi-agent workflows - Tool and action infrastructure with strong contracts, permissions, and approval boundaries - Retrieval, context engineering, evidence management, and persistent agent memory - Model-runtime engineering across multiple providers, latency profiles, and deployment environments - Evaluation, tracing, security, and operational control of nondeterministic AI systems - Designing reliable systems around LLM behavior in production environments Also include the introductory sentence: "We're looking for an experienced engineer who has beyond the prototype stage. You should be comfortable diagnosing nondeterministic failures, establishing clear boundaries between model judgment and deterministic software, and determining when workflows require autonomous execution, human approval, or conventional application logic." Could be a paragraph before list. Skills (Nice to Have) bullet list: - Experience deploying agent systems in government, defense, legal, healthcare, financial services, or other highly regulated environments - Familiarity with policy or legal research where temporal accuracy, provenance, and citation precision are critical - Experience operating self-hosted or multi-provider inference in restricted environments - Experience building agents that create durable artifacts or perform permissioned actions on behalf of users - Experience designing secure AI systems involving human-in-the-loop approvals and authorization boundaries Benefits bullet list: - Equity / ownership: Meaningful upside as the company grows. - Direct access to founders and CTO: This role reports directly to the CTO and works closely with the founding team. - High technical ownership: Own core agent-runtime infrastructure rather than a small component of a mature product. - Frontier agentic-AI work: Build production agents involving long-running workflows, memory, retrieval, model routing, tool use, evaluation, and security—not simply LLM API wrappers. - Early-stage impact: Materially influence architecture, engineering standards, and product direction. - Strong founding team: Leadership backgrounds include senior roles across government and major technology organizations. - Well-funded startup environment: Institutional backing provides the resources to build ambitious technology while retaining early-stage ownership and impact. - High-impact customer exposure: Build AI systems supporting government, policy, procurement, and other complex, high-stakes environments. - SoHo / NYC office: Work directly alongside the technical and founding teams in a highly collaborative environment. Pay paragraph: "Salary: $200,000 - $285,000 per year. Up to $285,000 base salary for Staff-level candidates, based on experience, plus equity." Schedule paragraph: "Full-time, in-person position in SoHo, New York City, with team members expected to work from the office five days per week when not deployed with customers." We might also mention "Certain customer engagements may require background checks, security reviews, access approvals, or eligibility for a U.S. government security clearance. Some projects may also be subject to U.S. citizenship or other customer-specific access requirements." That's more about requirements maybe but could be included in Responsibilities? It's more about working conditions. Could add to Schedule or a separate section? But we already have Schedule; maybe add to Schedule paragraph. However that is not strictly schedule; it's about clearance. Could be part of Benefits? Not really. Could be part of Requirements? It's a condition. Might be better to include in Schedule paragraph as additional note. But we