Description

• You will own problems end-to-end, taking ideas from initial exploration through to production deployment and ongoing iteration.
• You will design, build, and deploy AI agents that operate reliably in real-world environments, not just prototypes or demos.
• You will integrate AI systems into products, APIs, and business processes, ensuring they are usable and scalable.
• You will work closely with engineering teams to ensure systems are robust, observable, and maintainable in production.
• You will make pragmatic decisions that balance model performance, system latency, and cost efficiency.

Core Requirements

• You have strong Python skills and can write clean, production-grade code, with a solid understanding of system design principles.
• You have proven experience shipping LLM-powered systems into production, with clear examples of real-world usage – Deployed LangChain/LangGraph solutions or similar
• You have hands-on experience building AI agents or agentic workflows, including tool use, orchestration, and multi-step reasoning.
• You have designed and implemented RAG systems that deliver meaningful improvements, rather than simple prototypes.
• You are familiar with MCP or similar orchestration patterns, enabling structured context handling and tool integration – FastMCP/FastAPI
• You understand LLM limitations and trade-offs, and can design systems that mitigate issues such as hallucination, latency, and cost.
• You have experience deploying systems in cloud environments (AWS, GCP, or Azure) using modern engineering practices

Key Skills

Education

Any Gradute