Chooses problems based on measurable impact
Moves from idea → prototype → production in days or weeks
Ships at both layers: internal leverage and customer-facing product
Adapts quickly as models, tools, and best practices evolve
This is a 0→1 role with company-wide visibility.
What you'll do
Design and ship customer-facing AI products like ask.workos.com http://ask.workos.com, AI support bots embedded in customer Slack channels, and new surfaces we haven't built yet
Build internal tools that become part of people's daily work: agents, automations, and workflows that are stable, observable, and easy to maintain
Work on big bets: a unified bot framework, a sandboxed coding harness agent, and infrastructure that lets the entire company ship
Use LLMs, embeddings, retrieval, and tool-calling to plug into docs, Slack, GitHub, CRM, analytics, support systems, and internal services
Replace repetitive, multi-step manual processes with orchestrated, AI-driven flows that span multiple apps and data sources
Stay current on new models and tooling, run focused experiments, and help the team converge on patterns, libraries, and infrastructure that compound over time
Example problems you might work on
A sandboxed coding harness that can safely take a bug report or feature spec all the way to a deployed change
A unified bot framework that powers every AI touchpoint, internal and customer-facing from a single, observable backbone
A GTM intelligence layer that gives reps live account context, meeting prep, and follow-up from CRM, product usage, and conversation history
Turning noisy, cross-tool workflows (tickets, Slack threads, docs) into a single agent that handles triage, routing, and suggested actions
Infrastructure that lets any WorkOS team ship a reliable internal AI app without reinventing the stack
What we're looking for
You've taken AI-powered systems from idea to production and through at least one iteration cycle with real users
Strong engineering fundamentals. You're comfortable owning services, data flows, and integrations end-to-end
Experience building with LLM APIs
You think about failure modes, observability, and ownership, not just whether the demo works
Bias toward action. You care less about the model and more about removing real bottlenecks, saving hours, or unlocking workflows the company couldn't do before
Comfort with ambiguity and fast change. The problem, the tools, and the "right" patterns are all evolving, you're excited to help define them
Nice to have
Prior work on customer-facing AI products
Experience with embeddings, retrieval/RAG architectures, and structured tool-calling or agents
Exposure to MCP or similar protocols for connecting AI agents to real systems
Benefits and Perks (US Only) 💖
At WorkOS, we offer resources that emphasize personal and familial well-being. We offer healthcare coverage for you and your family, including medical, dental, and vision. We offer parental leave, paid-time off and fully remote working arrangements.
401k matching
Competitive Equity
Healthcare, dental and vision coverage
FSA, ST/LT Disability, Voluntary Life
Carrot fertility benefits
20 days paid vacation + 10 holidays + unlimited sick leave
12 weeks fully paid parental leave
Fitness: Monthly stipend for gyms, yoga classes, race registrations or whatever keeps you active
Wellness: Monthly stipend for a massage, meditations class, therapy, or activities that enhance your well-being
Commuter benefits for hybrid employees in SF/NYC
Unlimited token usage!
Please inquire directly with our recruiting team for benefits available to those working outside the US.
Equal Opportunity Employer
WorkOS is an equal opportunity employer, committed to diversity and inclusiveness. We will consider all qualified applicants without regard to race, color, nationality, gender, gender identity or expression, sexual orientation, religion, disability or age.
We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.
