At Bumble, we’re on a mission to create a world where all relationships are healthy and equitable. The Bee AI team is reimagining how people meet by introducing an intelligent, AI-powered product that sits alongside Bumble Date - helping members connect in more curated, thoughtful, and human ways, while preserving the magic of matching and conversation at the core of the Bumble experience.
This is a highly impactful individual contributor role with broad influence across engineering, product, and data. You’ll operate as a technical leader within the Bee AI team, setting direction for how we build, evaluate, and scale AI agents - while collaborating with purpose, taking ownership, and seeing ideas through to real-world impact.
What You'll Do
Lead the design, build, and extension of production AI agent systems for Bee, creating more curated ways for members to meet within a distinct AI-driven product experience
Architect and evolve Python-based services and agent workflows using PydanticAI and GCP, with a strong focus on reliability, extensibility, and maintainability
Define and improve how we build agents end to end, including prompt management, context handling, response schemas, fallback logic, and versioning practices
Establish robust evaluation approaches for agent quality, including offline and online evaluations, experimentation frameworks, telemetry, and clear success criteria for agent behaviour
Build repeatable patterns for monitoring, debugging, and managing agents in production, including observability, performance analysis, and continuous improvement loops
Partner closely with Product, Design, and Data within the Bee AI team to turn ambiguous opportunities into shipped features, while collaborating effectively with adjacent teams where integration is required
Apply strong technical judgment to responsible AI development by assessing outputs for quality, bias, safety, and transparency, ensuring human oversight where it matters most
Act as a technical leader by setting a high bar for code quality, system design, and delivery, collaborating with purpose, taking ownership, and demonstrating an agile mindset in line with our values of Courage, Respect, and Excellence
About you
Typically requires 8–10 years of experience, though we welcome candidates with alternative backgrounds that demonstrate equivalent skills.
You bring deep software engineering experience in production systems, with strong Python expertise and a track record of building scalable backend services
You have hands-on experience building or guiding AI and ML-powered product experiences, especially around AI agents, prompt design, context orchestration, and evaluation strategies
You are comfortable designing schema-validated LLM interactions, managing prompts and response structures, and creating deterministic fallbacks and safeguards for production use
You have experience with cloud infrastructure on GCP and know how to design systems with strong observability, resilience, and operational clarity
You are skilled at defining technical approaches for ambiguous, high-impact problems, using independent judgment while influencing across teams and creating alignment
You know how to build evaluation and feedback loops for AI systems, including instrumentation, experimentation, monitoring, and iterative improvement of agent behaviour over time
You collaborate effectively across disciplines, take ownership of outcomes, and adapt quickly as priorities evolve, demonstrating an agile mindset and working with purpose
You use AI thoughtfully in your own work to improve speed, quality, and learning, while ensuring responsible, inclusive, and human-centred application
Location
This role is based in Austin, and we ask that you’re within a commutable distance to this office, so that you’re able to come onsite regularly to collaborate across engineering teams.
We have a hybrid environment that requires you to be in the office Monday - Wednesday.
Please note: We are unable to offer Visa sponsorship at this time
