Job Description :

- 5 - 7 years of hands-on cloud architecture experience across at least two of AWS, GCP, and Azure - not certifications alone, but systems you have actually designed and operated under load.

- 2 - 3 years working directly with GenAI technologies - LLMs, vector stores, embedding pipelines, RAG architectures, or agentic frameworks in production.

- Deep familiarity with Node.js / npm runtime architectures and how they behave in containerized, cloud-native deployment environments.

- Experience designing multi-tenant SaaS infrastructure with enterprise security requirements - auth, audit, access control, isolation boundaries.

- Proven ability to architect deployment pipelines for codebases, APIs, and AI inference services - not just CI/CD for web apps.

- Familiarity with vector databases (Qdrant, Pinecone, or equivalent) and the infrastructure patterns around embedding generation and semantic retrieval at scale.

- Comfort with Python-based backends (FastAPI or equivalent) - you do not need to write all the code, but you need to own the infrastructure it runs on.

- Experience with infrastructure-as-code (Terraform or equivalent) - Terraform is already in the Synapse stack.

Key Responsibilities :

- Architect and maintain highly available, scalable cloud infrastructure across GCP, AWS, and Azure to support intensive AI model inference and data processing.

- Automate infrastructure provisioning and lifecycle management using Terraform to ensure consistency and speed across development and production environments.

- Design and implement high-performance vector database solutions using Qdrant to enable low-latency retrieval for complex AI agent workflows.

- Integrate and optimize CrewAI frameworks and Anthropic model pipelines to enhance the efficiency and reliability of our autonomous agent systems.

- Develop and maintain internal APIs using FastAPI to facilitate seamless communication between our infrastructure services and external client applications.

- Establish and manage Model Context Protocol (MCP) standards to ensure interoperability and data integrity across our distributed AI ecosystem.

- Collaborate with cross-functional teams to troubleshoot performance bottlenecks and implement proactive monitoring strategies that improve overall system uptime.