Senior Software Engineer, Backend/Investigative Agent

Senior Software Engineer, Backend/Investigative Agent WHO IS FLOCK? Flock Safety is the leading safety technology platform, helping communities thrive by taking a proactive approach to crime prevention and security. Our hardware and software suite connects cities, law enforcement, businesses, schools, and neighborhoods in a nationwide public-private safety network. Trusted by over 5,000 communities, 4,500 law enforcement agencies, and 1,000 businesses, Flock delivers real-time intelligence while prioritizing privacy and responsible innovation. We’re a high-performance, low-ego team driven by urgency, collaboration, and bold thinking. Working at Flock means tackling big challenges, moving fast, and continuously improving. It’s intense but deeply rewarding for those who want to make an impact. With nearly $700M in venture funding and a $7.5B valuation, we’re scaling intentionally and seeking top talent to help build the impossible. If you value teamwork, ownership, and solving tough problems, Flock could be the place for you. THE OPPORTUNITY We're hiring a Senior Backend Engineer to lead the architectural evolution of Nightshift, a conversational AI assistant that helps investigators surface critical evidence and close cases faster. This isn't just about wrapping an LLM; it’s about building the "brains" of an investigative agent. You will design the orchestration backend that manages complex LLM interactions, develop high-performance integration pipelines connecting our AI to Flock's massive data platform, and build the agentic framework that allows Nightshift to "act" on behalf of investigators. This is a ground-floor opportunity to solve the reliability and scaling challenges of deploying AI in high-stakes, real-time investigative workflows. You’ll partner with ML engineers on agentic workflows and platform teams to design robust APIs that ground AI in truth, ensuring our system remains performant as we process billions of data points daily. THE SKILLSET - Love for writing clean, performant code and a track record of building production-grade backend systems. - Strong proficiency in Python and TypeScript (Node) for building scalable web services, open to Go as well. - Experience with agentic patterns, including function calling, tool use (MCP), and orchestrating multi-step LLM workflows. - Ability to write and optimize complex SQL queries and data access patterns to ensure LLMs are grounded in real-time data without sacrificing latency or system performance. - Deep understanding of OpenAI/Anthropic/Gemini APIs, prompt engineering, and managing complex conversation state/context. - Proven ability to build seamless API integrations with LLMs, managing the bridge between unstructured model outputs and structured internal services through robust error handling and schema validation. - Strong database confidence with PostgreSQL, OLAP Databases, and Redis. You know how to use the right tool for the job to ensure fast retrieval. - Experience with microservice-oriented architecture and designing for scale (we handle 1B+ images daily). - Proficient with AWS services, Kubernetes (EKS), Docker, and CI/CD build tooling. - You thrive in "zero-to-one" environments, taking ambiguous problems and turning them into technical roadmaps. - Experience with LLM evaluation (LangSmith/Langfuse), vector search/RAG, or infrastructure-as-code (Terraform). 90 DAYS AT FLOCK The First 30 Days: - Familiarize yourself with Flock’s investigative workflows and the massive data pipelines that power our platform. - Pair with ML (agentic systems), Data Engineering (investigative datasets), and Platform teams to understand the existing API landscape. - Complete your first push to production. Pick up initial sprint tickets focused on API integrations, backend bug fixes, or performance tuning for LLM streaming. The First 60 Days: - Implement the backend orchestration layer for LLM tool calling and multi-step reasoning. - Design and build t ... (truncated, view full listing at source)