The role involves designing, optimizing, and maintaining prompts to enable agentic AI assistants to reason, plan, and execute tasks across various tools and workflows. The position focuses on multistep reasoning, tool usage, and the implementation of orchestration frameworks. Responsibilities include evaluating agent performance, identifying and mitigating failure modes, and documenting reusable patterns to enhance autonomy and efficiency. The work supports enterprise-level assistants and integrations across multiple systems and APIs. Collaboration with engineering and product teams is required to define agent roles, constraints, and guardrails.

Candidates must possess four to five years of experience in data science, machine learning engineering, software engineering, or applied AI. Necessary technical proficiencies include hands-on experience with large language models, prompt engineering techniques, and Python. Applicants are required to have experience designing prompts for multistep reasoning and tool-using agents, as well as familiarity with LLM APIs and agent frameworks. Additionally, the role requires strong communication and documentation skills to analyze agent outputs and improve performance.