Software Engineer - Data Agent & Agentic Search

ByteDance; San Jose (CA); On-site; USD 150,000 - 220,000; Full time

Job summary

ByteDance is building a next-generation Agentic Search platform in San Jose, blending planning, retrieval, and reasoning across structured data, documents, images, audio, and video. The team focuses on AI-powered search, multimodal retrieval, and enterprise-grade cloud services with a strong open-source footprint.

You will contribute to agentic search innovations, RAG, and scalable vector and full-text search systems while collaborating with experts in AI and data engineering to deliver impact

Qualifications

• B.S in Computer Science, AI, ML or related field.
• Strong coding, data structures and algorithms.
• Familiar with LLMs, Agents, Search, RAG or IR.
• Strong problem-solving, learning and communication skills.

Responsibilities

• Build Agentic Search and Analytics systems combining planning, retrieval, reasoning, tool execution and loop iterations.
• Develop multi-source and multimodal search across structured data, documents, images, audio and video.
• Create a unified semantic layer for heterogeneous enterprise data, including entities, metrics, metadata and relationships.
• Explore semantic accumulation and self-evolving agents improving via interactions and memory.

Skills

Coding & algorithms

LLMs & IR

Problem solving & communication

Education

B.S in Computer Science or related field

Tools

Python

Java

C++

Golang

Job description

Responsibilities

About the Team: The Search team is dedicated to building a fully managed, one-stop platform for information retrieval and analytics. Deeply compatible with Elasticsearch, OpenSearch, and Milvus, the platform serves four core scenarios—GenAI applications, search, security, and observability and provides comprehensive capabilities across full-text search, vector search, geospatial search, and hybrid search. We are also building next-generation Agentic Search products, including RAG, AI-powered search and multimodal retrieval, continuously pushing the boundaries of intelligent search technology. We are deeply involved in the open-source ecosystem and have contributed hundreds of PRs across the OpenSearch, Elasticsearch, Lucene and Milvus communities. Several members of our team hold key leadership roles in these communities, including Governing Board Member, Technical Steering Committee Member, PMC Member and Maintainer, helping shape the evolution of the broader search and database ecosystem through sustained technical contributions. On the business side, we not only provide reliable infrastructure for some of ByteDance’s largest-scale vector and full-text hybrid search workloads, but also deliver enterprise-grade cloud search services to external customers through Volcano Engine, helping businesses unlock growth through data. We embrace a pragmatic yet ambitious engineering culture: while continuously publishing innovative research at top-tier conferences such as VLDB and ICDE, we remain strongly focused on real-world impact and commercial adoption, building a comprehensive product portfolio that serves a wide range of search and AI use cases. Our team brings together leading database researchers and exceptional engineers from around the world. We are looking for talented individuals with expertise in search or vector database engine development, distributed systems architecture or AI model innovation to join us. Together we will explore uncharted technical territory, define the data foundation for the AI era and empower both ByteDance and enterprises across industries to achieve AI-driven transformation.

Responsibilities

• Build Agentic Search and Analytics systems that combine planning, retrieval, reasoning, tool execution and iterative agentic loops.
• Develop multi-source and multimodal search across structured data, documents, images, audio and video.
• Build a unified semantic layer for heterogeneous enterprise data, including entities, metrics, metadata and relationships.
• Explore semantic accumulation and self-evolving agents that continuously improve through interactions, feedback, memory and historical executions.

Qualifications

Minimum Qualifications

• B.S in Computer Science, AI, Machine Learning or a related field.
• Strong coding, data structures and algorithm skills; proficient in Python, Java, C++ or Golang.
• Familiarity with LLMs, Agents, Search, RAG, Information Retrieval or Machine Learning.
• Strong problem-solving, learning and communication skills.

Preferred Qualifications

• Experience with Agentic Search, Data Agents, RAG or AI Search through research, internships or projects.
• Familiarity with Elasticsearch/OpenSearch, Milvus, Faiss, Qdrant or similar retrieval systems.
• Experience with tool calling, MCP, Skills, memory, planning or agent evaluation.
• Experience with semantic layers, knowledge graphs, multimodal retrieval or large-scale data processing.

About Us

Founded in 2012, ByteDance's mission is to inspire creativity and enrich life. With a suite of more than a dozen products, including TikTok, Lemon8, CapCut and Pico as well as platforms specific to the China market, including Toutiao, Douyin and Xigua, ByteDance has made it easier and more fun for people to connect with, consume and create content.

Why Join ByteDance

Inspiring creativity is at the core of ByteDance's mission. Our innovative products are built to help