Backend Engineer, Applied AI

We need to output HTML fragment with sections: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Only include sections that have real specific content. We must not repeat job title. Must not include Job ID. Must not include boilerplate. Must preserve all substantive info. Must not invent or summarize away detail. Must not create sections with filler like "commensurate with experience". Must only include sections when posting has real specific content. We need to parse the posting for content. Let's extract sections: - About Citizen: description of company, mission, product. That's "About the role"? Actually "About Citizen" is about company. Could map to "About the role"? The instruction says use

for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we can use "About the role" heading for description of role? But we have "About Citizen" which is about company. Might still fit under "About the role"? Probably we can use "About the role" to describe the role and company context. We'll include substantive content: description of Citizen, mission, product, real-time system, etc. - Responsibilities: list of what you will own, tasks: own core pieces of system, ship with small team, build for Mission Control, etc. Also "What You Will Own" section lists pieces: real-time pipeline, live video infrastructure, AI in pipeline, internal operator tooling, enterprise API, infrastructure and cost. Also "Your First 90 Days" details tasks. Also "How Success is Measured". Also "You will also build for the people inside Citizen who run the city." So we can extract responsibilities. - Requirements/Qualifications/Skills: The "Who You Are" section lists requirements: built and run backend systems at consumer scale, real-time, fluent in Go, comfortable in Python, Kubernetes, cloud stack, carried pager, worked on live video, put ML models/LLMs into production, build with AI, measure, high agency, care about mission, want to be in NY office. Also "Compensation" is Pay. - Benefits: Not explicitly listed besides equity. There's mention of equity in compensation. Also maybe "On-call" details could be considered schedule? On-call rotation: roughly one week every two months, 24/7 for urgent emergencies. That's schedule info. Also maybe "Benefits" could include equity, maybe health etc not mentioned. So we may include Pay section with base salary and equity. Schedule section with on-call details. - Benefits: Not much else. Could we include "Benefits" as equity? But equity is part of compensation. Might be better to put equity under Pay. Benefits maybe none. We should not create empty sections. Thus we will include sections: About the role, Responsibilities, Requirements, Qualifications, Skills, Pay, Schedule. Possibly combine Requirements/Qualifications/Skills as separate if content distinct. The "Who You Are" includes many bullet-like statements; we can split into Requirements (experience), Qualifications (education? none), Skills (technologies). But we can just make one section "Requirements" with all. However instruction says prefer few substantive sections over many thin ones. So we could combine into one "Requirements" covering experience, skills, qualifications. But they ask to use headings for each of those categories if content exists. We need to decide. We have content for: experience (built backend systems, real-time), technical skills (Go, Python, Kubernetes, cloud, ML/LLM, agents), soft skills (high agency, measurement, mission). Could split into Requirements (experience), Skills (technologies), Qualifications (maybe none). But we can include Qualifications if we have any (like degree not mentioned). Safer to not create Qualifications if no specific content. Thus sections: About the role, Responsibilities, Requirements, Skills, Pay, Schedule. Now we need to extract precise sentences, preserve all substantive info, not invent or summarize away detail. Must not omit details. Must include all substantive info. That's a lot. We need to include everything from posting that is substantive, but we can rephrase? The instruction: "Preserve ALL substantive information; do NOT invent or summarize away detail." Means we should not leave out details, but we can rephrase? Probably we should keep the information but can format as lists. Must not omit any detail. That's tough because the posting is long. We need to include everything: description of Citizen, mission, product, real-time system, what you will own, first 90 days, how success measured, who you are, compensation, on-call, etc. We must not include boilerplate like cookie/navigation/legal/EEO etc. There's none. We need to output only HTML fragment, no markdown fences. We'll create sections with

and then

for prose,

• for lists. We need to ensure we don't repeat job title. Let's draft. First, About the role: include description of Citizen and role context. We'll write a paragraph summarizing: Citizen is #1 safety app, live network, newsroom, safety tool, ingests from 911 radio, CAD, user video, partner feeds, detection, verification, geolocation, distribution to millions, live video infrastructure, enterprise products/API, etc. Also mention that you will own core pieces, work with small team, human and agent engineers, build for Mission Control, etc. But we must preserve all substantive info: maybe we need to include each sentence. That would be huge. However we can combine into paragraphs as long as we don't lose info. The instruction likely expects we keep the meaning but not necessarily verbatim. "Do NOT invent or summarize away detail" suggests we shouldn't omit details, but we can paraphrase as long as we keep all details. That's ambiguous. Safer to keep bullet points covering each distinct piece. Let's extract distinct pieces: From "About Citizen": - Citizen is the #1 safety app in the U.S. - Every day, thousands of videos are captured live at the scene of real incidents and distributed in real time to people in every major American city. - No other consumer product has this. - It is a live network, a newsroom, and a safety tool at once, and it is growing again. - Underneath it is a real-time system: ingest from 911 radio, CAD feeds, user video, and partner feeds; detection, verification, and geolocation; distribution to millions of devices in seconds; the live video infrastructure that carries the scene to the app; and the enterprise products and API that deliver the same intelligence to cities, hospitals, campuses, and private security. From "You will own core pieces of that system and ship them with a small team of engineers, human and agent." - You will also build for the people inside Citizen who run the city. - Our Mission Control and real-time operations team lives in ProtectOS and Regulator, our internal operating tools, all day. - A meaningful share of backend work is tooling for them, and they are the most demanding users you will have. From "Why Now": - Citizen is being rebuilt as an AI-native company, and the backend is where most of the rebuild happens. - AI now sits in the pipeline itself, detecting and verifying incidents and deciding what people see, and the system has to get faster, more accurate, and cheaper per incident while it does. - The enterprise business is working and needs to scale on the same platform. - That is a very large amount of interesting work for a very small number of people who use agents to carry it. From "How We Work": - Every role at Citizen is two things: the craft, and the operation of AI to multiply it. - You are a backend engineer first: distributed systems judgment, taste in code, and the instinct to know where a real-time system will break before it does. - You are also the person who runs agents to write, review, test, and operate the code alongside you. - You propose where agents run alone; production gates are policy, because this is a safety product. - You hold the bar on correctness and you keep the hard calls for yourself. - If in month three you are still hand-writing CRUD, migrations, or runbooks, something has gone wrong. - How work is organized: Engineering runs on a driver and builder model. Every initiative is a drive with one accountable driver who owns scope, sequencing, and tradeoffs, and a small set of builders who ship it with them. Drivers are not assigned by seniority; they are the people who want the decision and the responsibility that comes with it. You will build on other people's drives and you will drive your own, early. - On-call: Citizen runs around the clock and so does the backend. On-call is a rotational program: roughly one week every two months, and when you carry the pager you are available 24/7 for the most urgent emergencies, with resolution expected in hours, not days. Everyone on the team carries it. Say now if that is not for you. From "What You Will Own": - We Are Not Hiring a Caretaker For The Whole Backend. We Are Hiring Someone Dedicated, Who Wants Ownership And Can Carry It, Over a Real Piece Of The Core System, Chosen By The Team's Need First And Your Interest Second, And Who Is Equally Willing To Own New Ideas And New Services Where They Move The Company's Growth And Current Focus. - The Pieces On The Table Today: - The real-time pipeline. Ingest from 911 radio, CAD feeds, user video, and partner feeds; detection, verification, geolocation, and distribution to millions of devices in seconds. Correctness, latency, and cost per incident are the three numbers. - Live video infrastructure. Ingest from the phone, the restreamer, and delivery through Mux to every viewer. One of the largest cost and latency lines in the company. - AI in the pipeline. The services that put models and agents into the path from raw signal to published incident: evaluation, provenance, guardrails, and the staged path from human-in-the-loop to autonomous operation behind audited gates. - Internal operator tooling. The backend behind ProtectOS and Regulator, the tools Mission Control uses to verify, write, and publish incidents. When these are slow or wrong, the city hears about it late. - Enterprise, API, MCP, and partners. The services behind the enterprise consoles; developing and supporting the public API and MCP access, which is how enterprise customers and agents will consume Citizen data; and partner integrations that put Citizen inside the systems cities already run, including our integration with Axon. - Infrastructure and cost. Go and Python services on Kubernetes (GKE) in Google Cloud, Pub/Sub, MySQL and Postgres, BigQuery, and the observability that lets a small team run a large system. - Whichever Piece You Take, Two Things Come With It: - Instrumentation. Registering Segment events with the data team, checking them in BigQuery, and making sure the numbers leadership sees are the numbers the system produced. - The agent loop. The agents that draft, review, test, and operate backend code at Citizen. You extend and operate them, you propose where they run alone, and you raise the output bar. You work daily with iOS and Android on the contracts, with ML on the models, with Data on events, and with Mission Control as your primary internal user. From "Your First 90 Days": - Days 1–30: Read the code. Use the product every day in New York. Sit on the Mission Control floor through a live incident and watch how ProtectOS and Regulator are actually used. Ship to production in week one. Join the on-call rotation as a shadow. Identify the three things that will break first and start on the first. - Days 31–60: Drive your first initiative end to end. Land one measurable improvement in latency, correctness, or cost. Take your first solo on-call week. Extend the agent loops already wired into the backend repo and propose the first one to run without a human, in test generation, review, or on-call triage. - Days 61–90: Ship the first AI-in-p