At nOps, we're building the future of cloud cost optimization through automation, intelligence, and simplicity. We're looking for a Senior Backend Engineer who has hands-on experience building and scaling AI agents in production, especially using LangChain and modern LLM stacks. This role is perfect for someone who thrives at the intersection of infrastructure, automation, and applied AI.

What You'll Do

• Design, build, and scale backend systems that power AI agents to optimize cloud infrastructure.
• Implement and productionize solutions using LangChain, OpenAI, Bedrock, and other LLM APIs.
• Build modular, reusable, and composable chains/agents that automate real business workflows (e.g., cloud resource optimization, anomaly detection, policy enforcement).
• Collaborate with product, DevOps to bring intelligent experiences to life.
• Optimize agent performance, latency, and reliability at scale.
• Contribute to architectural decisions that shape nOps' intelligent automation platform.
  
  

What We're Looking For

• 5+ years of experience in backend engineering (Python preferred).
• Experience with LangChain and LLM orchestration tools (e.g., OpenAI, Bedrock, HuggingFace).
• Proven track record of deploying AI/LLM agents in production environments.
• Experience with FastAPI, RESTful APIs, and cloud-native architectures.
• Familiarity with AWS services, cloud cost optimization, or FinOps is a plus.
• Ability to work autonomously in a fast-paced startup environment.
  
  

Bonus Points

• Experience with vector databases (e.g., Pinecone, Weaviate, FAISS).
• Knowledge of prompt engineering, agent memory, and retrieval-augmented generation (RAG).
• Contributions to open-source LLM tools or frameworks.
  
  

Why nOps?

• Make a real impact helping companies save millions in cloud waste.
• Work with a team that's passionate about cloud, AI, and building smarter software.