Job Description

Team Introduction
Join the Innovative BytePlus Team!
As part of BytePlus, you will help enterprises and AI-native developers build the next generation of their businesses. By leveraging ByteDance’s cutting-edge technologies in AI models, agent solutions, and cloud infrastructure, we are committed to developing innovative products and solutions that shape the future. We enable our clients to focus on what matters most, and you can play a key role in helping us achieve that mission.

We are looking for talented individuals to join our team. As a graduate, you will get opportunities to pursue bold ideas, tackle complex challenges, and unlock limitless growth.
Successful candidates must be able to commit to an onboarding date by the end of the year. Please state your availability and graduation date clearly in your resume.
Candidates can apply to a maximum of two positions and will be considered for jobs in the order you apply. The application limit is applicable to our Company and its affiliates' jobs globally. Applications will be reviewed on a rolling basis - we encourage you to apply early.

Responsibilities
- Bridge the gap between cutting-edge Generative AI model research and real-world industrial applications by solving the “last mile” of AI deployment, ensuring models are performant, grounded, and effectively integrated into complex agent solutions that deliver direct business impact.
- Design and prototype AI-native agent solutions based on client requirements, including agent workflows, system integrations, and LoRA fine-tuned models tailored to specific industry use cases, such as automated credit risk summaries for fintech or style-specific image and video generation.
- Deliver production-ready implementations by writing high-quality code to integrate AI model APIs into agent frameworks such as ADK and LangChain, together with supporting components such as RAG, vector databases, memory systems, cache management, and skills.
- Optimize system performance across latency, throughput, and cost dimensions by improving prompt chains and implementing scalable caching strategies for AI features serving large user bases.
- Develop evaluation frameworks and guardrails, including LLM-as-a-judge and human-in-the-loop approaches, to ensure outputs are safe, accurate, and reliable, especially for compliance-sensitive industries such as finance. Evaluate multiple models on common tasks to identify trade-offs and inform go-to-market decisions.
- Collaborate closely with product and algorithm research teams to feed real-world customer signals back into the product roadmap and model development process.