Flock Safety is the leading safety technology platform, helping communities thrive by taking a proactive approach to crime prevention and security. The Software Engineer III role involves building a conversational AI assistant to aid investigators in surfacing critical evidence and closing cases faster, focusing on both product thinking and technical execution.
Responsibilities:
- Design and implement the conversational interface for Night Shift
- Build the orchestration backend that manages LLM interactions and tool calling
- Develop integration pipelines connecting AI to Flock's existing data platform and APIs
- Collaborate closely with ML engineers on prompt engineering and agentic workflows
- Maintain a strong point of view on user experience
- Familiarize yourself with Flock's mission, investigative workflows, and customer use of the platform
- Pair with engineers across Cloud Software and ML teams to understand existing APIs, data models, and system architecture
- Build relationships with key stakeholders to understand their capabilities and constraints
- Complete a first-day push to production
- Pick up initial sprint tickets: bug fixes, small UX improvements, or API integrations
- Participate in customer feedback sessions to understand investigator workflows and pain points
- Deliver core conversational UI components and establish patterns for chat interfaces
- Implement backend orchestration for LLM interactions and tool calling
- Stand up observability for the AI system (logging, tracing, basic metrics)
- Own end-to-end features that connect UI, backend orchestration, and data integrations
- Collaborate with Product to rapidly iterate based on early user testing
- Lead development of a core Night Shift capability that demonstrably improves investigator efficiency
- Represent the team in cross-functional initiatives, balancing zero-to-one experimentation with engineering best practices
- Establish patterns for testing and quality in an evolving AI product
- Influence product roadmap through technical insights and customer feedback
- Mentor team members on LLM integration patterns or full-stack best practices
Requirements:
- Love for coding and continuous learning, especially in the rapidly evolving LLM space
- Resourceful problem-solver mindset: excel in ambiguous situations and take initiative to define product direction
- Strong TypeScript / Node / Express skills for web services and API design (REST, SSE, WebSockets for streaming)
- Modern web framework expertise (React / TypeScript preferred), particularly for conversational UI and chat interfaces
- Hands-on LLM experience: OpenAI/Anthropic/Gemini APIs, prompt engineering, streaming responses, and conversation context management
- Familiarity with agentic patterns: function calling, tool use (MCP), and orchestrating multi-step workflows
- API integration skills: consume existing APIs or design new ones to ground AI in investigative data
- Database confidence: PostgreSQL and sophisticated SQL for data retrieval
- Cloud infrastructure basics: Docker, Kubernetes (Helm), AWS services (S3, SQS, API Gateway)
- Product-minded: translate user feedback into technical requirements and make pragmatic tradeoffs
- Ability to obtain and maintain Criminal Justice Information Services (CJIS) certification as a condition of employment
- Bonus points for: LLM evaluation tools (LangSmith, Langfuse), vector search/RAG, microservices architecture, or Terraform