Staff Software Engineer - AI Copilot (Backend)

Role overview

Lead the backend architecture and delivery for a conversational AI copilot that helps customer service administrators configure and improve their systems through natural language. This staff-level role combines hands-on engineering with technical direction across a team and adjacent groups, covering the path from design through production operation.

Responsibilities

- Set the technical direction for conversational backend capabilities, including language-model orchestration, intent detection, context retrieval, and tool execution. - Own complex features through design, implementation, release, and ongoing production support. - Establish engineering standards and make architecture decisions that support reliable, scalable services. - Work with machine learning scientists, product, design, and engineering partners to shape the technical roadmap. - Develop evaluation approaches, safeguards, and safety mechanisms for language-model features in production. - Mentor engineers and address systemic risks, performance constraints, and reliability gaps.

Requirements

- At least eight years of software engineering experience, including technical leadership in backend systems. - Strong experience designing distributed systems at scale, including APIs, services, and data pipelines. - Production experience integrating large language models, such as orchestration, prompt design, evaluation, safeguards, or multiple model providers. - Fluency in a backend language such as Ruby, Python, or Go, with working ability in additional languages. - Deep understanding of AWS, containerized deployments with Docker and Kubernetes, and CI/CD. - Experience setting technical direction and aligning teams, plus clear communication and sound judgment in ambiguous situations.

Nice to have

- Background in conversational AI, model serving, inference pipelines, or model evaluation. - Familiarity with event-driven systems, SQL, data platforms, or experimentation tools such as Metaflow and MLflow. - Experience technically leading or mentoring a group of three or more engineers.

Benefits and work setup

- Hybrid work, with in-person collaboration at an office for part of the week and remote flexibility for the remainder.