Role Overview
We are looking for a Principal AI Software Architect with a deep foundation in software engineering, backend systems, distributed systems, and large-scale application architecture, combined with hands-on experience building Generative AI and Agentic AI systems.
This is a Software & Systems Architecture role—not a Cloud Infrastructure or Solutions Architect role.
The ideal candidate has progressed from being a strong hands-on software engineer into a Staff Engineer, Principal Engineer, Software Architect, Systems Architect, or Distinguished Engineer, while continuing to design and build complex software systems.
You will be responsible for architecting next-generation AI-native software systems and transforming complex, long-lived enterprise applications into architectures that can be understood, operated, and progressively modernized using AI agents.
Key Responsibilities
- Architect and build production-grade Agentic AI systems integrated with complex enterprise software platforms.
- Design multi-step agent workflows involving reasoning, tool calling, orchestration, state management, context management, retries, checkpoints, and failure recovery.
- Enable AI agents to securely interact with APIs, databases, enterprise applications, developer tools, source-code repositories, build systems, testing frameworks, and CI/CD pipelines.
- Design and build MCP (Model Context Protocol) servers or equivalent tool-integration layers that allow AI agents to safely interact with enterprise systems.
- Apply LangGraph, LangChain, AutoGen, CrewAI, Semantic Kernel, OpenAI Agents SDK, or similar technologies where appropriate.
- Architect large-scale backend systems using distributed systems, microservices, event-driven architectures, messaging, APIs, and asynchronous processing.
- Drive modernization of complex legacy applications, including monolith decomposition, Strangler Pattern, service extraction, dependency modernization, and progressive architectural transformation.
- Build mechanisms that help AI agents understand large codebases, including code structure, dependencies, APIs, services, business rules, and execution flows.
- Explore and implement AI-assisted software engineering capabilities for code analysis, code generation, refactoring, test generation, dependency upgrades, vulnerability remediation, build execution, debugging, and automated validation.
- Design deterministic validation and governance mechanisms around AI-generated actions and code changes.
- Establish production-grade observability, evaluation, guardrails, authorization, auditability, security, and human-in-the-loop controls for Agentic AI systems.
- Remain hands-on with architecture, design, prototyping, and critical implementation while providing technical leadership to engineering teams.
Required Experience
- 12+ years of software engineering experience preferred. Exceptional hands-on candidates with 12–14 years of highly relevant experience may also be considered.
- Strong career foundation in backend/software engineering, with hands-on expertise in one or more of:
- Java, Python, Golang, Node.js, C++, or similar backend technologies.
- Deep understanding of distributed systems, concurrency, microservices, system design, APIs, event-driven architectures, messaging, and data systems.
- Strong experience designing and building high-scale, high-availability, resilient production software systems.
- Experience modernizing complex or legacy software platforms.
- Hands-on experience with LLMs, Generative AI, Agentic AI, AI agents, or AI-powered automation.
- Experience integrating AI systems with real-world tools, APIs, databases, enterprise systems, or software-development workflows.
- Strong understanding of software engineering fundamentals, including SOLID principles, design patterns, testing, observability, reliability, and security.
Highly Preferred
- Production experience building Agentic AI systems rather than only chatbots or basic RAG applications.
- Hands-on experience with MCP (Model Context Protocol).
- Experience with LangGraph or similar agent orchestration frameworks.
- Experience building multi-agent or long-running agent workflows.
- Experience with persistent agent state, memory/context management, checkpoints, retries, and resumability.
- Experience implementing agent tool calling and controlled execution of state-changing actions.
- Experience applying AI to the Software Development Lifecycle (SDLC).
- Experience building agents that interact with code repositories, builds, tests, CI/CD pipelines, developer tools, or security tooling.
- Experience with LLM evaluation, guardrails, agent observability, sandboxing, authorization, and human approval workflows.
