The Chinese AI startup DeepSeek is forming a new team to develop Code Harness, a tool for autonomous programming. This was announced by the company’s engineer, Deli Chen.
🚀 We’re hiring! DeepSeek is forming a new Harness team to build Code Harness from the ground up—maybe you can call it DeepSeek Code or something like this hhh🤣🤣🤣
📍 Based in Beijing. Two roles open:
— Deli Chen (@victor207755822) May 20, 2026
🧠 Harness Product Manager → https://t.co/vb3aWbYV9L
👨💻 Harness R&D…
The developer posted two job openings on social media: a product manager and a research and development engineer. Both positions are based in Beijing.
The new solution will directly compete with Claude Code from Anthropic and Codex from OpenAI.
According to Chen, the team will create Code Harness "from scratch." He described the project as "DeepSeek Code or something like that."
In the job descriptions, the company uses the formula "model + harness = agent."
The harness refers to a layer above the LLM, responsible for managing context, planning steps, memory, tool invocation, file handling, terminal operations, testing, and feedback.
DeepSeek aims to offer not just a typical code generation assistant, but an agent product capable of executing multi-step tasks in a development environment.
Candidates are expected to have experience with Claude Code, Codex, Cursor, GitHub Copilot, Manus, and OpenClaw. Other requirements include an understanding of agent cycles, MCP, multi-agent systems, context management, and vibe coding.
The team will work closely with DeepSeek researchers.
DeepSeek V4 supports integration with Claude Code through an Anthropic-compatible API. The recently released V4 Flash version, introduced on April 24, costs $0.14 per 1 million input tokens. In comparison, Claude Opus 4.7 is priced at $15 for the same volume.
It’s worth noting that in February, Anthropic accused three Chinese AI startups—DeepSeek, Moonshot, and MiniMax—of a large-scale campaign to leverage Claude to enhance their own models.