Senior AI Software Architect Ninja 🥷 (RAG, Vector DB, Agentic AI, Python Expert)

Location: United States or Canada Only >> Remote | Full-Time

Industry: AI-Driven Business Intelligence | SaaS | Data Analytics

NOTE: We are looking for senior level experience BUT if you are a Superstar Graduate that is an AI badass and want to come prove it to us... APPLY.

About the Role

We are looking for an experienced Senior AI Software Architect (or Junior Badasses) with deep Python expertise and in designing, building, and scaling modular RAG, Vector DB, Agentic AI architectures. In this role, you will take ownership of ensuring that our cloud-based AI platform is highly scalable, modular, efficient, and secure. Our AI-driven business intelligence platform seamlessly connects to hundreds of SaaS tools to provide real-time analytics, predictive insights, and automated decision intelligence to our clients.

You will drive architectural decisions, define best practices, and implement frameworks to ensure that our AI platform continues to scale seamlessly, utilizing a modern stack including Kubernetes, API Gateways, event-driven messaging, retrieval-augmented generation (RAG), vector databases, and robust microservices.

Check out our Reel 🎥🎬 >> https://youtu.be/Aff-rX9W_TE

Compensation:

The role offers approximately 1% to 2% of company equity, based on your involvement and contribution. This position represents a commitment to grow alongside our team. As we gain a little traction and raise capital, salaries will start to become available. We already have had over 300 companies in beta and have just started to charge for the services, which are doing really well, so we intend to provide some compensation soon in Q3 as revenues and capital fundraising efforts take off. Our pipeline for revenue is quite high right now, so we feel confident.

Key Responsibilities

Architect and Design Modular AI Software Framework

• Lead the design and development of modular architectures specifically for AI-driven applications. (Python EXPERTISE REQUIRED.)
• Define and implement service boundaries, ensuring clear interfaces, scalability, and independent deployments.
• Optimize system architecture for cost efficiency, high availability, performance, and extensibility.

AI Model Deployment and Integration

• Design robust patterns for AI model deployment, versioning, orchestration, and automated rollbacks.
• Implement model registry solutions and structured RAG-based workflows.
• Ensure seamless integration and performance optimization for vector databases and embedding stores (e.g., Pinecone, Milvus, Weaviate, Qdrant, Vertex AI Matching Engine).

Event-Driven Microservices Architecture

• Implement event-driven architectural patterns leveraging messaging platforms (Google Pub/Sub, Kafka, RabbitMQ).
• Design asynchronous communication pipelines enabling independent, scalable AI services.

API Gateway & Secure API Design

• Design API Gateway patterns for managing API versioning, authentication, and secure service-to-service interactions.
• Establish best practices for REST/gRPC API design, OAuth2 authentication, and role-based access control (RBAC).

Infrastructure and Deployment Collaboration

• Closely collaborate with infrastructure and DevOps engineers to deploy robust cloud-native architecture on Google Cloud Platform (GKE, Cloud Build, Terraform).
• Provide architectural oversight on infrastructure automation, CI/CD pipelines, and container orchestration strategies.

Required Skills & Experience

• Extensive hands-on experience architecting, building, and scaling modular, microservices-based AI software platforms.
• Proven track record designing AI-specific architectures including AI agents, retrieval-augmented generation (RAG), vector databases, and event-driven communication.
• Expertise in cloud-native architecture patterns and practices, ideally on Google Cloud Platform (GCP).
• Strong experience designing scalable APIs and API Gateway patterns (REST, gRPC, OAuth2, RBAC).
• Deep understanding of AI model deployment, model lifecycle management, and versioning strategies (MLflow, Vertex AI, or equivalent).
• Experience implementing asynchronous, event-driven messaging systems (Pub/Sub, Kafka, RabbitMQ).
• Familiarity with modern container orchestration and CI/CD best practices (Kubernetes, Docker, Terraform, GitHub Actions).

Preferred Qualifications

• Prior experience designing LLM-driven architectures and retrieval-augmented generation (RAG) solutions.
• Experience optimizing and scaling large language model (LLM) workflows.
• Familiarity with structured data retrieval frameworks such as LangChain or LlamaIndex.
• Knowledge of advanced data streaming solutions (Apache Flink, Redis Streams, Ray).

Why Join Us?

• Shape the architecture of an innovative AI-driven business intelligence platform.
• Play a strategic role guiding AI software best practices and scalable design.
• Join a high-performing, remote-first team focused on cutting-edge AI technology.
• Competitive compensation, career growth, and potential equity opportunities.