Responsibilities
- Design and prototype generative AI agents, workflows, system integrations, and industry-specific fine-tuned models for customer needs.
- Implement production-quality integrations with AI model APIs, agent frameworks, retrieval-augmented generation, vector databases, memory systems, caching, and tools.
- Optimize latency, throughput, cost, prompt chains, and caching strategies for AI features serving millions of users.
- Develop evaluation frameworks and guardrails using LLM-as-a-judge and human-in-the-loop methods to improve safety, accuracy, and compliance.
- Evaluate models on common tasks and provide field signals to product and algorithm research teams.
- Lead and mentor Solutions Architect teams across Korea and Japan and support regional growth.
Requirements
- Bachelor's degree in Engineering, Computer Science, or a related field.
- At least 5 years of related work experience in an AI-native industry, preferably as a Solutions Architect, product solutions professional, or Forward Deployed Engineer.
- Proven experience leading Solutions Architect teams.
- Deep understanding of AI solutions on public cloud and LLM applications across industry verticals such as e-commerce, social and entertainment, and FinTech.
- Knowledge of agentic AI design paradigms including Re-Act, Plan and Execute, Multi-Agent, and Skills.
- Practical AI infrastructure knowledge, including GPU selection and model inference acceleration frameworks such as vLLM and sglang.
- Proficiency in Python, FastAPI, PyTorch or Jax, and orchestration frameworks such as LangChain or LlamaIndex.
- Experience with Transformer architectures, RAG, prompt engineering, vector databases, SQL/NoSQL systems, Spark, Flink, Docker, Kubernetes, and cloud model deployment.
- Preferred experience serving large DNB and internet application clients, including applications with more than 1 million monthly active users.
- Ability to work independently in a fast-paced, ambiguous environment and foster team morale, set goals, and drive successful delivery.
Tech Stack
Categories
About ByteDance
ByteDance is a global incubator of platforms at the cutting edge of commerce, content, entertainment and enterprise services - over 2.5bn people interact with ByteDance products including TikTok. Creation is the core of ByteDance's purpose. Our products are built to help imaginations thrive. This is doubly true of the teams that make our innovations possible. Together, we inspire creativity and enrich life - a mission we aim towards achieving every day. At ByteDance, we create together and grow together. That's how we drive impact - for ourselves, our company, and the users we serve. We are committed to building a safe, healthy and positive online environment for all our users. We have over 110,000 employees based in more than 30 countries globally. Join us.