AI Agent R&D Engineer

Responsibilities

• Design and implement AI agent architectures based on LLMs, including task planning, dialogue management, and intent recognition.
• Develop and optimize prompt and Chain-of-Thought templates; automate prompt tuning and evaluation workflows.
• Build and maintain multi-agent collaborative systems and pipelines for complex scenario coordination.
• Collaborate with product, data, and ops teams to define interface specs, deploy CI/CD pipelines, and drive continuous delivery.
• Stay current with agent frameworks and open-source projects (e.g., LangChain, AutoGen, AgentKit) and integrate them into production.

Qualifications

• Proficient in at least one language: Python, Go, JavaScript, or TypeScript, with solid software architecture and engineering experience.
• Familiar with LLM usage and fine-tuning (e.g., GPT, LLaMA, Claude); hands-on project experience preferred.
• Deep understanding of prompt engineering—able to write and maintain high-quality prompt libraries and implement automated evaluation.
• Skilled in Docker/Kubernetes, microservices deployment; experienced with CI/CD and observability (monitoring, logging, alerting).
• Bachelor’s degree or higher in Computer Science, Software Engineering, AI, or related fields.
• Prefers experience with multi-agent frameworks or production-grade Agent platforms (like LangChain Agents, AutoGen, CrewAI).
• Familiarity with dialogue quality and safety evaluation metrics; experience in automated LLM output review and risk control.
• Capability in performance tuning for high-concurrency, distributed deployments, and cost optimization.

Benefits

We provide a competitive compensation package, opportunities for professional growth, participation in a discretionary equity incentive plan, and access to a comprehensive company benefits program, subject to eligibility requirements.