The Browser Company is building a better way to use the internet by creating a browser that can help users grow, create, and stay curious. The AI Foundations team specifically aims to build the architecture that powers AI capabilities in their browser, enabling rapid prototyping and shipping of innovative browser automation and AI-driven features, ensuring the AI assistant is accurate, trustworthy, and fast.
Requirements
- 8+ years of experience building and leading high-craft software systems, with deep expertise in backend or infrastructure engineering.
- Hands-on experience building with LLMs and integrating AI outputs into production systems; curiosity to go deep on how models work without doing model training.
- Proven ability to design, ship, and operate large-scale, reliable systems that support rapid experimentation and iteration.
- You've worked on large, complex codebases and understand how to improve systems to make them easier to understand, debug, and maintain.
- Strong technical leadership and mentoring experience; you elevate engineering quality through thoughtful code reviews, clear communication, and pragmatic execution.
Responsibilities
- Own and evolve the AI Foundations systems that integrate LLM outputs into product experiences, partnering closely with ML and Product Engineers to turn model output into reliable, production-quality features.
- Build and operate infrastructure for evals and prompt engineering, making it simple for teams to author, run, and interpret evals while safely versioning and rolling out prompts via tools, direct feedback, and product integrations.
- Orchestrate and optimize LLM usage across the service layer, standardizing formats, streaming, error handling, and cost controls, and closing the loop between evals, auto-tuning, and real-world performance.
- Partner across product and infrastructure teams to define requirements, SLAs, and APIs for AI features, turn dogfooding and live usage into evaluable scenarios, and build clear workflows and documentation that help teams ship confidently.
- Elevate engineering quality and team impact by leading high-impact projects, improving reliability and observability across systems, mentoring engineers, and owning planning and on-call for AI Foundations services as needed.
- Build a unified experience for editing prompts, running queries, and launching evals, with telemetry, dashboards, and alerts to monitor performance and catch regressions early.
- Develop tooling that surfaces expected vs. actual behavior, clusters failures, and automatically refines prompts to improve routing, tool use, and response quality.
Other
- We’re primarily focused on hiring in North American time zones and require that folks have 4+ hours of overlap time with team members in Eastern Time Zone.
- You’re pragmatic, motivated by nebulous problems, and excited to work in a startup environment with quick product validation cycles.
- Strong technical leadership and mentoring experience
- We strongly support diversity and encourage people from all backgrounds to apply.
