We are looking for a backend developer who can design, build, and deploy AI agents powered by large language models. This role requires strong backend engineering fundamentals combined with practical experience building production-grade LLM systems. The ideal candidate is comfortable using AI tools to accelerate development and can architect reliable systems around non-deterministic models. You will be responsible for building scalable agent infrastructures, integrating LLM APIs, and creating robust backend systems that power intelligent workflows. Key Responsibilities Design and implement backend systems for AI agents using LLMs Architect agent workflows including memory, tool use, retrieval, and multi-step reasoning Build and maintain APIs that expose AI-powered capabilities Integrate vector databases, embeddings, and retrieval systems Implement evaluation pipelines to measure agent performance and reliability Optimize latency, cost, and scalability of LLM-based systems Develop secure authentication, logging, monitoring, and observability layers Use AI coding assistants to increase development speed while maintaining code quality Write clean, testable, and maintainable production code Collaborate with product and frontend teams to translate requirements into technical solutions Required Skills Strong backend development experience (3+ years preferred) Proficiency in Python or Node.js Experience building APIs using frameworks such as FastAPI, Express, Django, or similar Hands-on experience with LLM APIs (OpenAI, Anthropic, open-source models, etc.) Experience building AI agents, tool-calling workflows, or RAG pipelines Familiarity with vector databases (Pinecone, Weaviate, FAISS, etc.) Solid understanding of databases (SQL and NoSQL) Experience with cloud platforms (AWS, GCP, or Azure) Experience deploying containerized applications using Docker Strong debugging and system design skills Preferred Qualifications Experience with LangChain, LlamaIndex, or similar orchestration frameworks Experience fine-tuning or hosting open-source models Familiarity with distributed systems and asynchronous processing Experience building evaluation and monitoring pipelines for LLM outputs Knowledge of prompt engineering and structured output design Prior experience building multi-agent systems AI Usage Requirement This role requires active use of AI coding tools. Candidates must demonstrate: Ability to use LLMs to scaffold systems and accelerate development Skill in reviewing, debugging, and refining AI-generated code Judgment in validating correctness, security, and performance of AI-assisted outputs Ability to design systems that combine human engineering oversight with AI productivity What We Value Systems thinking Clear communication and documentation Bias toward shipping Ownership and accountability Ability to operate in ambiguous environments