Senior AI Backend Engineer

Circadence is hiring a Senior AI Backend Engineer to help build the next generation of Range

GPT—an intelligent cyber range design and analysis platform that fuses LLM-driven reasoning, Lang Graph orchestration, and real-time infrastructure automation.

Range

GPT enables cybersecurity professionals to design and deploy realistic training environments through natural-language interaction and AI-powered scenario generation. You’ll be responsible for building the backend systems that make this possible—developing scalable APIs, integrating language-model workflows, managing stateful orchestration, and connecting AI agents with infrastructure services.

This role is ideal for an engineer who loves designing robust, high-performance systems, working with LLM integrations, and solving challenging problems at the intersection of AI, data modeling, and distributed orchestration.

• Design and implement Lang Graph-based AI orchestration workflows, connecting LLM agents, RAG pipelines, and infrastructure provisioning logic.
• Build and maintain backend services using Python (Django/FastAPI) that drive Range
  
  GPT’s AI, data, and orchestration layers.
• Develop and optimize RESTful APIs for tool-calling agents, context retrieval, and real-time inference operations.
• Implement Postgre
  
  SQL data models for graph-structured context, AI workflow checkpoints, and user interaction histories.
• Integrate vector retrieval and semantic search frameworks (PGVector, Weaviate, etc.) to support RAG-based reasoning.
• Collaborate with AI engineers on model context injection, inference proxy routing, and workflow persistence strategies.
• Contribute to infrastructure automation and Dev Ops pipelines using Docker, Kubernetes, and Azure Dev Ops.
• Participate in architecture discussions focused on scalability, modularity, and performance optimization.
• Provide backend support for Range
  
  GPT’s canvas-based interface and agentic design workflows.

• 7+ years of experience in backend or full-stack roles, with a strong focus on backend architecture and systems design.
• Expert-level proficiency in Python, with production experience using Django and/or FastAPI.
• Demonstrated experience building LLM-based workflows using Lang Graph (or a similar orchestration framework).
• Strong understanding of REST API design, asynchronous processing, and service-oriented architecture.
• Deep knowledge of Postgre
  
  SQL schema design, optimization, and query performance.
• Practical experience integrating LLMs and RAG pipelines, including context injection, function/tool calling, and multi-step orchestration.
• Hands-on experience deploying and maintaining applications in containerized environments (Docker, Kubernetes).
• Solid understanding of CI/CD best practices, observability, and production operations.
• Strong software engineering fundamentals—testing, debugging, and system reliability in distributed systems.

• Experience with semantic retrieval and agentic workflow orchestration in AI systems.
• Familiarity with RAG architectures, vector databases, or embedding stores.
• Background in cybersecurity, simulation tooling, or infrastructure-as-code systems.
• Knowledge of Model Context Protocol (MCP) or similar orchestration standards.
• Experience working with multi-model inference backends (Azure OpenAI, Anthropic, local inference servers).
• Proficiency in distributed systems, task queues, and message brokers (Celery, Rabbit
  
  MQ, Redis).

https://(Use the "Apply for this Job" box below)./