> Markdown version of [/jobs/ext/516347-staff-software-engineer-agents](https://www.wearedevelopers.com/jobs/ext/516347-staff-software-engineer-agents). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Staff Software Engineer, Agents - **Company:** Flock Safety - **Location:** United States (Remote available) - **Salary:** $200,000.0 - $220,000.0 - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Amazon Web Services, Big Data, Cloud Computing, Databases, Software Debugging, Software Reliability Testing, Software Engineering, WebSocket, WebRTC, Large Language Models, Multi-Agent Systems, Backend, AI Platforms, Kubernetes, Production Code, Vertica - **Published:** June 13, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=945a5f4007dbea78 ## About the Role * Strong backend/software engineering fundamentals * Experience shipping production code and customer-facing products at scale * Experience with LLMs, AI systems, and agentic workflows in production * Familiarity with tools like LangChain, CrewAI, OpenAI SDK, or Claude Agents SDK * Strong product and customer mindset * Comfortable working in ambiguity and startup-style environments * Experience with cloud infrastructure, databases, and backend systems * Strong collaboration, ownership, and communication skills Nice to Have * RAG systems * Multi-agent systems * Voice agents * AI evals and reliability testing * AWS, Kubernetes, ClickHouse, WebSockets/WebRTC Feeling uneasy that you haven't ticked every box? That's okay; we've felt that way too. Studies have shown women and minorities are less likely to apply unless they meet all qualifications. We encourage you to break the status quo and apply to roles that would make you excited to come to work every day., If an offer is extended and accepted, this position requires the ability to obtain and maintain Criminal Justice Information Services (CJIS) certification as a condition of employment. Applicants must meet all FBI CJIS Security Policy requirements, including a fingerprint-based background check. ## Description Our team is building Nightshift, a conversational investigative agent that helps law enforcement investigators surface critical evidence, reason across complex data, and close cases faster. Nightshift sits at the intersection of large-scale data systems, production AI, agentic workflows, and high-stakes customer use cases where reliability, transparency, and speed matter. You will join a small, senior team that combines application development and ML testing expertise. We are looking for another high-level engineer who can accelerate our agent development, raise our engineering bar, and help turn our work into a reusable AI platform for other product teams across Flock. This is not a research-only role. You will ship production systems, improve agent reliability through testing and evals, build infrastructure for faster iteration, and design backend systems that allow AI products to safely and reliably operate on top of Flock's large-scale data platform. You will be expected to own ambiguous, high-impact technical problems end to end, influence architecture across teams, and serve as a multiplier for engineers building AI-powered customer experiences at Flock., We prescribe to 90 day plans and believe that good days lead to good weeks, which lead to good months. This serves as a preview of the 90 day plan you will receive if you were to be hired in this role at Flock. The First 30 Days * Meet the team, understand the Nightshift product vision, and build context on our architecture, customer workflows, and investigative use cases. * Immerse yourself in customer calls, chat transcripts, production traces, and support feedback to understand where the agent succeeds and where it breaks down. * Get fluent in our AI observability and debugging tools, including Langfuse, and begin triaging real agent behavior. * Ship your first production change, followed by multiple small improvements that build familiarity with the codebase and product surface area. * Identify a recurring agent failure pattern and turn it into a fix, test, ticket, or concrete technical recommendation. The First 60 Days * Meet the team, understand the Nightshift product vision, and build context on our architecture, customer workflows, and investigative use cases. * Immerse yourself in customer calls, chat transcripts, production traces, and support feedback to understand where the agent succeeds and where it breaks down. * Get fluent in our AI observability and debugging tools, including Langfuse, and begin triaging real agent behavior. * Ship your first production change, followed by multiple small improvements that build familiarity with the codebase and product surface area. * Identify a recurring agent failure pattern and turn it into a fix, test, ticket, or concrete technical recommendation. 90 Days & Beyond * Take end-to-end ownership of a meaningful area of the Nightshift agent architecture. * Have a significant architectural improvement designed, vetted, and underway. * Improve the team's ability to reproduce, evaluate, debug, and safely ship changes to agent behavior. * Create patterns, libraries, workflows, or platform capabilities that other teams at Flock can use to build AI-powered product experiences. * Multiply the team through technical leadership, design reviews, pairing, PR reviews, and architecture input that persists beyond your direct involvement. * Serve as a credible technical voice with customers and internal stakeholders, translating between real investigative workflows and engineering direction. ## Related Videos - [Agentic employees in world's most downloaded FinTech app](https://www.wearedevelopers.com/videos/100123-agentic-employees-in-world-s-most-downloaded-fintech-app) - [Transforming Education: A Journey from interactive Markdown to Remote-Labs](https://www.wearedevelopers.com/videos/941-transforming-education-a-journey-from-interactive-markdown-to-remote-labs) - [Developing the Backend with Stefan Lingler, CTO at Shpock](https://www.wearedevelopers.com/videos/100360-developing-the-backend-with-stefan-lingler-cto-at-shpock) - [On a Secret Mission: Developing AI Agents](https://www.wearedevelopers.com/videos/1510-on-a-secret-mission-developing-ai-agents) - [Hello JARVIS - Building Voice Interfaces for Your LLMS](https://www.wearedevelopers.com/videos/1641-hello-jarvis-building-voice-interfaces-for-your-llms) - [Nest.js - TypeScript in the backend can also be clean](https://www.wearedevelopers.com/videos/1033-nest-js-typescript-in-the-backend-can-also-be-clean) ## Related Articles - [Dev Digest 134 - Where pixels sing?](https://www.wearedevelopers.com/magazine/477-dev-digest-134-where-pixels-sing) - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers) - [Fully Remote Software Engineer Jobs](https://www.wearedevelopers.com/magazine/447-fully-remote-software-engineer-jobs) - [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix)