Agentic systems architect

Want to design the architecture that lets AI agents safely refactor, test and ship production code? Then let's talk. Our client acquires enterprise software companies and turns them into AI-native, profitable, scalable businesses. They are a remote-first, AI-forward team spread across the globe, offering high ownership, flexibility and impact, work across multiple products and technologies, and growth pathways across engineering, product and leadership. The job: transform a 10+ year legacy codebase into a high-velocity, agent-operable architecture, at the intersection of software architecture, AI-agent orchestration and engineering governance.

• Decompose legacy monoliths into agent-readable, modular systems with strict boundaries and single responsibility
• Lead incremental modernization using the Strangler Pattern, wrapping legacy logic in modern, contract-driven interfaces
• Enforce SOLID principles, Dependency Injection, and Hexagonal Architecture to ensure deterministic AI execution and low regression risk
• Architect and maintain the agent context layer: standardized Skills, Rules, and Commands for AI-driven engineering workflows
• Build and operate Model Context Protocol (MCP) servers exposing legacy APIs, services, and databases as typed, secure, AI-consumable tools
• Own contract-first API design as the primary interface between human intent and autonomous agent execution
• Act as architectural gatekeeper for AI-generated pull requests, ensuring scalability, security, and long-term maintainability
• Mandate test-driven development (TDD) and characterization testing to preserve legacy behavior during refactoring
• Monitor and optimize agentic reasoning loops to balance cost, speed, and architectural integrity

• 7+ years in software architecture, platform engineering, or technical leadership
• Proven experience modernizing large, undocumented legacy systems
• Deep hands-on expertise with TypeScript, .NET, and Node.js
• Strong background in API design, distributed systems, and modular architectures
• Practical experience with agentic development, MCP, LLM tooling, or AI-assisted engineering
• Bias toward clean code, deterministic systems, and production-grade AI
• Будет плюсом: Experience with remote-first or globally distributed teams; Background in SaaS transformations, scale-ups, or PE-backed environments; Comfort operating in high-ambiguity, high-ownership settings

• Contract, full-time
• Fully remote from Eastern Europe, working US morning hours (Scrum).