Senior Software Engineer, Intelligence

Flock

9d•$170,000 - $200,000•Onsite

About The Position

As Flock scales its investigative platform, building capabilities that directly accelerate how investigators surface critical evidence is essential to helping agencies resolve cases faster. You will design reliable backend systems, build agentic integration frameworks, and ensure our AI tools remain accurate, performant, and grounded in real-time data. This role centers strictly on backend microservices, database access patterns, API design, and LLM orchestration. You will build production-grade, low-latency infrastructure capable of handling high-volume data streams safely.

Requirements

Demonstrated capability writing performant production code in Python or TypeScript to build scalable backend web services and microservices.
Deep database proficiency with PostgreSQL, OLAP databases, and Redis to optimize complex data access patterns and real-time retrieval without sacrificing latency.
Practical experience implementing agentic workflows, function calling, Model Context Protocol tools, and prompt engineering with major LLM APIs.
Strong background in cloud-native infrastructure, including hands-on experience with AWS, Kubernetes, Docker, and CI/CD pipelines.
Demonstrated capability taking ambiguous technical problems in zero-to-one product spaces and translating them into clear architectural roadmaps.

Nice To Haves

Experience with LLM evaluation frameworks, vector search, or infrastructure-as-code is a plus.

Responsibilities

Lead the architectural evolution and backend execution for Flock's investigative workflows.
Design and deploy high-performance orchestration backends that manage complex LLM tool-calling, function execution, and multi-step reasoning workflows.
Engineer high-throughput integration pipelines and secure connectors linking conversational interfaces directly to core data platform microservices.
Partner with Machine Learning and Data Engineering teams to bridge unstructured LLM outputs with structured internal APIs, maintaining strict schema validation and error handling.