Role Overview
As a Senior Software Engineer on the Airfam Products team, you'll be instrumental in building Airbnb's next generation of AI-powered employee experience platforms. Your work will be a force multiplier for the entire company—every AI feature you ship, every system you architect, and every engineer you mentor will amplify productivity across Airbnb's global workforce. You'll be joining the AI for Non-Developers workstream, focused on expanding AI productivity tools to all Airbnb employees—building OneChat Agents, deep research capabilities, artifact creation tools, and task automation that make AI accessible to everyone, regardless of technical background.
Responsibilities
- Lead the technical design and implementation of LLM-powered features for OneChat and enterprise AI tools, including RAG pipelines, AI agents, and prompt optimization.
- Partner with product managers, designers, and cross-functional teams to translate user problems into AI-powered solutions that serve Airbnb's global workforce.
- Develop and iterate on agentic AI capabilities, including multi-step reasoning, tool use, and context-aware decision-making.
- Implement evaluation pipelines and quality systems to measure model performance, detect hallucinations, and ensure responsible AI practices.
- Own production AI systems end-to-end, including deployment strategies, monitoring, alerting, and incident response.
- Collaborate with the DevAI team on AirChat SDK integrations, MCP (Model Context Protocol) implementations, and Glean Action Packs.
- Mentor engineers (L6-L8) through design reviews, architecture discussions, and pair programming sessions.
- Stay current with the rapidly evolving GenAI landscape, evaluating new models and techniques for potential application.
- Balance hands-on technical contributions with technical leadership activities.
Required Expertise
- 8+ years of software engineering experience, with significant focus on building production AI/ML systems.
- 2+ years of hands-on experience with Large Language Models (LLMs), including fine-tuning, prompt engineering, embeddings, and retrieval-augmented generation (RAG).
- Strong proficiency in backend technologies (TypeScript, Go, or Java).
- Strong backend and distributed systems expertise, including API design (REST, GraphQL) and cloud infrastructure (AWS, GCP, or Azure).
- Track record of shipping AI-powered products from prototype to production.
- Proven ability to collaborate cross-functionally and influence without authority.
- Excellent communication skills with ability to distill complex technical concepts for diverse audiences.
- Bachelor's degree in Computer Science, Engineering, or equivalent practical experience.
Preferred Expertise
- Master's or PhD in Computer Science, Machine Learning, or related field.
- Experience building AI agents and multi-agent systems, preferably using Claude.
- Experience building integrations using MCP.
- Experience with containerization and orchestration (Docker, Kubernetes).
- Background in building enterprise-grade internal tools and developer productivity platforms.
- Experience with frontend technologies (React, Next.js) for full-stack AI product development.
- Contributions to open-source Gen AI/ML projects or publications at top venues.