Solutions Architect - BytePlus - Seoul

Join the Innovative Byte Plus Team:

As part of Byte Plus, you'll help enterprise customers build what's next for their business. Leveraging Bytedance's cutting-edge technologies, we are devoted to developing innovative products and solutions to shape the future. We help our clients to focus on what truly matters. Centering on innovation and excellence, we create game-changing solutions that help businesses to unleash their potential. You can help us to achieve our mission.

Responsibilities:

1. Bridge the gap between our cutting-edge Generative AI research on models and real-world industrial applications. You aren't just shipping code; you are solving the "last mile" problem of AI—ensuring models are performant, grounded, and integrated into complex agent solutions to deliver results directly, in verticals like e-commerce, ads, social & entertainment, enterprises, etc
2. AI-native agent solution design & prototyping: Rapidly design and iterate AI agents based on clients' requirements, prototype workflows and system integrations, LoRA fine-tuned models tailored to specific industry needs (e.g., automated credit risk summaries for Fintech, or design style specific image/video content generation).
3. Production-ready implementation and delivery: Write production-quality code to integrate AI model APIs in various agent frameworks (ADK, Lang Chain, etc) with necessary tools (RAG, vectorDB, memory base, cache management, skills, etc)
4. Performance Optimization: Tackle challenges around latency, throughput, and cost. You’ll optimize prompt chains and implement caching strategies to ensure AI features scale for millions of users.
5. Evaluation & Guardrails: Develop rigorous evaluation frameworks (LLM-as-a-judge, human-in-the-loop) to ensure outputs are safe, accurate, and hallucination-free—critical for compliance-heavy industries like Finance. Also to evaluate various models on the same tasks to conclude on the pros and cons for GTM.
6. Cross-functional Collaboration: Work with product and Algorithm research teams to feed "field signals" back into the core product roadmap.

• Technical Skills Involved
• AI/ML: Deep understanding of Transformer architectures, RAG, prompt engineering, and vector databases (e.g., Pinecone, Milvus, Weaviate).
• Engineering: Proficiency in Python (FastAPI, Py Torch/Jax) and experience with orchestration frameworks like Lang Chain or Llama Index.
• Data Systems: Comfort with SQL/NoSQL and data processing at scale (Spark, Flink).
• Cloud/DevOps: Experience with Docker, Kubernetes, and deploying models on cloud providers.

Requirements:

• Minimum Qualifications

• Engineering Bachelor degree and above;

• At least 1~2 years of related work experience in AI-native industry, preferably in the role of solution architect, product solution or forward deployed engineer (FDE)

• Product-wise, preferably have deep understanding in AI solutions on Public Cloud, including but not limited to: LLM applications in industry verticals like e-commerce, social & entertainment, Fin Tech, etc

• Agentic AI design paradigms

• Re-Act, Plan and Execute, Multi-Agent, Skills, etc

• AI Infra practical knowledge such as GPU selections and model inference acceleration frameworks (vLLM, sglang, etc)

• High fluency in oral and written English

• Preferred Qualifications

• Industry-wise, preferably, have worked with large DNB & internet app clients in verticals like e-commerce, social & entertainment apps, gaming, etc, with at least over 1M monthly active users

• Excellent communication skills in English and/or Chinese, as well as Korean (both written and verbal)

• Comfortable with fast-paced and ambiguous "startup" environment

• Can-Do attitude, Self-starter, Ability to work independently and highly motivated with contagious enthusiasm;

• Team player and able to foster positive team morale, to set goals and drive for successful fulfilment;

• Gives attention to Details as much as to the "Bigger Picture"; Can synthetize.