Senior Software Engineer: AI-Native Application

Zoom • San Jose, CA

10h • Hybrid

About The Position

We are looking for a backend engineer with a passion for AI-native application to help us build the next generation of Contact Center applications. In this role, you will design and implement the systems that reason, plan, and execute complex analytical tasks reliably. You will work at the intersection of traditional software engineering and AI-native experience development, creating robust frameworks and complex problem-solving.
About the Team Zoom Contact Center is Zoom’s next-generation cloud-based customer engagement platform. Our team is at the forefront of this evolution, building an AI-powered analytics engine that acts as a virtual data analyst for our customers. We are moving beyond traditional reporting to create intelligent agents capable of understanding natural language and reasoning through complex data problems. We provide actionable insights to improve contact center efficiency.

Requirements

• Hold a BS or MS in Computer Science, Engineering, or a related field, with 5+ years of professional software engineering experience.
• Develop backend systems using Java (Spring Boot) or Python, including RESTful APIs and microservice-based architectures.
• Design AI agent–based applications using advanced reasoning and orchestration patterns such as ReAct, Chain-of-Thought (CoT), and multi-agent systems.
• Engineer and optimize prompts for complex reasoning tasks, while managing LLM context windows and long-term memory using techniques such as vector databases.
• Model and maintain scalable data solutions with a solid understanding of SQL and NoSQL database design.
• Apply data analysis and statistical concepts to inform system design and AI behavior evaluation.
• Implement real-time AI response delivery using streaming protocols such as Server-Sent Events (SSE) or WebSockets.
• Build high-concurrency, asynchronous systems using modern async programming models (e.g., Java CompletableFuture, Reactive Streams).
• Implement and debug distributed, multi-agent systems using observability tools and distributed tracing frameworks like OpenTelemetry.
• Create production-grade AI evaluation and orchestration pipelines (LLMOps).
• Leverage vector databases (e.g., Pinecone, Milvus), semantic search, AI orchestration frameworks (e.g., LangChain, Semantic Kernel, AutoGen), and large-scale data platforms or OLAP databases (e.g., ClickHouse).

Responsibilities

• Building AI-native Systems: Design and implement robust AI-native contact center architectures (e.g., ReAct, Multi-Agent Systems) that can autonomously plan and execute complex workflows.
• Developing Backend scalable services using Java and Spring Boot to support high-performance AI applications.
• Designing and optimizing prompt strategies, context management systems, and agent memory to ensure high accuracy and relevance in LLM responses.
• Building logic for decomposing ambiguous user requests into executable steps, handling dependencies and error recovery in non-deterministic AI flows.
• Engineering observability and evaluation frameworks to monitor agent performance, latency, and correctness in production.
• Partnering with data scientists and product managers to translate complex analytical requirements into reliable engineering solutions.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees