About this Role:We are seeking a seasoned Senior AI Architect to design, architect, and deliver transformative, end-to-end intelligent software solutions leveraging Large Language Models (LLMs). In this strategic role, you will lead architectural initiatives, driving scalability, reliability, and user-focused outcomes within our core technology stack (FastAPI/Python, Next.js/TypeScript, GCP), using Cursor as your primary development environment.
As our Senior AI Architect, you will architect and oversee the implementation of robust AI-enabled microservices designed for direct integration into applications, as well as MCP (Model Context Protocol) servers that provide abstraction and structured, context-aware interactions for AI agents. Your vision will shape our products, improve decision-making, and significantly enhance user engagement and scalability. You will own strategic architectural decisions to ensure our AI infrastructure is modular, performant, and built for long-term scale.
Key Responsibilities:- Architect and lead development of scalable, end-to-end LLM-powered agentic systems, including strategic planning, memory management, structured prompt engineering, and multi-agent orchestration.
- Define, implement, and optimize MCP-compliant servers, establishing robust, modular, and context-rich interactions among AI components.
- Provide strategic direction and technical leadership for developing APIs and backend services using FastAPI to orchestrate complex agent workflows.
- Oversee design and development of dynamic, performant frontend applications built in Next.js for intuitive user interaction with intelligent systems.
- Lead architectural planning and execution of deployments on Google Cloud Platform (Cloud Run, GKE, Cloud Functions), ensuring high availability, scalability, and cost efficiency.
- Implement sophisticated multi-agent coordination using orchestration frameworks such as AutoGen, CrewAI, or LangGraph, ensuring cohesive, structured reasoning among distributed agentic components.
- Design and optimize integrations with vector databases (e.g., Qdrant), establishing schemas and pipelines for efficient long-term memory, semantic search, and retrieval.
- Act as a technical liaison between product, engineering, and infrastructure teams to align architecture with business strategy; mentor engineers on best practices for AI architecture, scalability, and performance.
Required Skills and Experience:- 5-8+ years of full-stack software engineering experience, with at least 2+ years explicitly focused on architecting AI-driven production systems.
- Proven ability to architect and deliver complex, scalable solutions leveraging LLMs (OpenAI, Hugging Face, etc.).
- Deep experience with Python (FastAPI), TypeScript (Next.js), and extensive knowledge of GCP infrastructure.
- Demonstrated expertise in designing or significantly contributing to MCP servers or similar structured context-management systems.
- Advanced knowledge of orchestration patterns, multi-agent systems, and frameworks (AutoGen, CrewAI, LangGraph).
- Strong experience designing integrations and schema structures for vector databases (e.g., Qdrant).
- Proficiency with Cursor, or a strong willingness to adopt it fully as your primary development tool.
Nice to Have:- Experience leading teams or major projects involving LLM-powered multi-agent orchestration.
- Deep understanding of agent tool integrations (search APIs, code execution environments).
- Proven skill in advanced prompt engineering, chaining methodologies, and task decomposition.
- Experience with LLM evaluation frameworks and debugging complex distributed agent environments.
- Contributions to open-source projects related to MCP-compatible or agent-based systems.
What's In It For You:- The opportunity to architect and deliver cutting-edge, production-level intelligent systems using advanced LLM and multi-agent technologies.
- Strategic ownership of AI-driven systems leveraging the Model Context Protocol, significantly influencing our technical direction.
- A highly collaborative, innovation-driven environment using modern development tools and best practices.
- Visibility and leadership opportunities within a team shaping the future of AI infrastructure and applications.
- Comprehensive health coverage (medical, dental, and vision)
- Company-paid life and disability insurance
- Optional benefits like pet insurance, legal, and supplemental health plans
- 401(k) with day-one eligibility, 3% safe harbor, plus up to 2.5% company match
- Generous time off: 10 paid holidays and PTO starting at 15 days, growing up to 25
- Access to Consertus Academy for continuous learning and development
How to Apply:If you're passionate about advancing AI-driven infrastructure and shaping the future of intelligent systems, we'd love to hear from you. Apply today!
