Key skills
AWSCloudDistributed SystemsGoogle Cloud PlatformGraphQLJavaJavaScriptKubernetesNext.jsPythonReactTerraformTypeScriptGoAIMachine LearningMLLLMLarge Language ModelsOpenAIClaudeAnthropicRAGLangChainAgenticLangGraphGCPGoogle CloudLeadershipCommunication
About this role
Role Overview
- Lead the technical design and implementation of LLM-powered features for OneChat and enterprise AI tools, including RAG pipelines, agent orchestration, 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
- Architect and build production-ready AI/ML-integrated systems, ensuring scalability, reliability, and low latency across multi-cloud environments
- 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, safety, and user satisfaction
- 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 emerging AI technologies and evaluate their applicability to employee experience products
- Balance hands-on technical contributions with technical leadership activities.
Requirements
- 8+ years of software engineering experience, with significant focus on building production AI/ML systems
- Deep understanding of Large Language Models (LLMs) including fine-tuning, prompt engineering, embeddings, and retrieval-augmented generation (RAG)
- Strong proficiency in Python and at least one additional language (TypeScript, Go, or Java)
- Experience building and deploying production ML systems at scale with high availability and low latency requirements
- Strong backend and distributed systems expertise, including API design (REST, GraphQL) and cloud infrastructure (AWS, GCP)
- 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 the ability to distill complex technical concepts for diverse audiences
- BS in Computer Science, Engineering, or equivalent practical experience.
- Master's or PhD in Computer Science, Machine Learning, or related field (preferred)
- Experience with AI agent frameworks (LangChain, LangGraph, or similar) and agentic development patterns (preferred)
- Experience integrating foundation model APIs (OpenAI, Anthropic/Claude, Google) (preferred)
- Familiarity with ML evaluation systems, including LLM-as-a-judge approaches (preferred)
- Experience with containerization and orchestration (Kubernetes), infrastructure-as-code (Terraform) (preferred)
- Background in building enterprise-grade internal tools and developer productivity platforms (preferred)
- Experience with frontend technologies (React, Next.js) for full-stack AI product development (preferred)
- Publications at top AI/ML venues a plus (preferred).
Tech Stack
- AWS
- Cloud
- Distributed Systems
- Google Cloud Platform
- GraphQL
- Java
- JavaScript
- Kubernetes
- Next.js
- Python
- React
- Terraform
- TypeScript
- Go
Benefits
- This role may also be eligible for bonus, equity, benefits, and Employee Travel Credits.