Design, build, and iterate on AI Assistants integrated with enterprise tools including Jira, Slack, and internal data sources
Develop and maintain prompt engineering frameworks, evaluation pipelines, and feedback loops to continuously improve assistant quality and reliability
Build and maintain APIs, backend services, and integrations that connect AI capabilities to the tools teams already use
Collaborate with AI Ops, security, IT, and platform engineering teams to ensure systems are production-grade, secure, and observable
Contribute to a repeatable framework for building new AI Assistants as the program expands
Enable the organization by building a marketplace of shared skills/plugins
Evaluate new models, tools, and libraries and make informed recommendations on when and how to adopt them
Identify and mitigate risks related to AI outputs, data handling, and responsible use
Contribute to technical documentation, runbooks, and onboarding materials that help the team scale what gets built
Requirements
4+ years of software engineering experience, with at least 1 year focused on building with AI and/or creating LLM-powered applications
Experience building and deploying apps in cloud infrastructure
Hands-on experience with LLM APIs (OpenAI, Anthropic, or similar) and the practical realities of prompt engineering at scale
Experience leveraging Claude Code for agentic coding
Experience integrating with third-party APIs and enterprise tools (Jira, Slack, or similar platforms is a plus)
Experience with software engineering best practices including: version control, testing, CI/CD, observability, and code review
Strong communication skills and the ability to work with non-technical stakeholders to understand workflows and translate them into technical requirements.
Tech Stack
Cloud
Benefits
Health Insurance Coverage (medical, dental, and vision)