AI Architect (LangChain Ecosystem) - Remote

CentralSquare Technologies•,

1d•Remote

About The Position

At CentralSquare, we don’t just build software - we power public servants and uplift communities with Hero-Grade Technology. Every line of code, every feature we deliver helps heroes across North America protect, serve, and save lives. When you join us, you become part of a mission-driven team creating technology that makes communities safer and stronger. Your Growth Matters. We believe heroes deserve opportunities to rise. That’s why we invest in your career with mentorship, learning programs, and clear paths for advancement. If you’re motivated, there’s no limit to how far you can go. Your Commitment Deserves Reward. We offer competitive compensation and a benefits package designed to support your life inside and outside of work—tuition reimbursement, parental leave, paid volunteer hours, and unlimited PTO. Plus, our flexible work environment gives you the freedom to balance your heroic work with personal well-being, whether you’re in the office or remote. Join us and help build the tools that power real-life heroes. Together, we make a difference.

Requirements

Deep fluency with the LangChain ecosystem
Familiarity with emerging Model Context Protocol (MCP) standards
Experience with scalable Python/TypeScript service design
Experience architecting retrieval-augmented, agent-based, and graph-enhanced AI applications
Experience with prompt lifecycle management, evaluation harnesses, observability hooks, and guardrail layers
Experience building and maintaining Python and TypeScript SDK layers, agent tooling, and shared libraries
Experience with evaluation frameworks like RAGAS and LangSmith tracing

Nice To Haves

Experience with LangChain/LangGraph

Responsibilities

Define and govern MCP server contracts, tool manifests, and inter-agent messaging patterns across multi-agent workflows built on LangChain/LangGraph.
Architect end-to-end RAG and GraphRAG pipelines — from embedding strategy, vector store selection, and graph construction through retrieval orchestration and context-window management
Design system-level architecture for AI applications, including prompt lifecycle management, evaluation harnesses, observability hooks, and guardrail layers.
Lead technical design reviews, establish AI engineering best practices, and mentor mid-level engineers on LLM application patterns.
Partner with product and data teams to translate business problems into retrieval and reasoning strategies; prototype rapidly and document architectural decisions.
Build and maintain Python and TypeScript SDK layers, agent tooling, and shared libraries consumed by application teams.
Drive evaluation frameworks — RAGAS, LangSmith tracing, and custom evals — to measure retrieval quality, hallucination rates, and task completion.
Stay current with frontier model capabilities, contribute to model selection criteria, and surface architecture changes required by new API or context-window evolutions.