Senior AI Engineer

[About the Role]

We are seeking a Senior AI Engineer to design, build, and scale next-generation AI-assisted products, including:
1. Q&A system based on advanced Retrieval-Augmented Generation (RAG) systems
2. Agentic programming workflows based on technical specifications
3. Knowledge management automation, document intelligence, and semantic search
4. AIBIOS and internal automation platforms that enhance enterprise productivity

In this role, you will transform product requirements into scalable AI systems, including LLM pipelines, agent frameworks, fine-tuned models, and production-quality services.

You will collaborate closely across various engineering teams to bring AI products from prototype → production → continuous improvement → scaling.

[Responsibilities]

1. Design and implement scalable AI architectures, including LLM pipelines, RAG systems, agentic workflows, and orchestration layers.
2. Develop production-grade AI features for Q&A, summarization, extraction, automation, and knowledge workflows.
3. Build reusable components such as tool integrations, vector retrieval stages, evaluation pipelines, and model-serving modules.
4. Establish best practices for model versioning, experiment tracking, data governance, and quality assurance.
5. Diagnose system bottlenecks and ensure reliability, scalability, and cost efficiency of AI systems.
6. Support the end-to-end lifecycle of agent-based AI products from development, launch, monitoring, to iterative enhancement.

[Minimum Qualifications]

1. Bachelor’s degree (or equivalent practical experience).
2. 5+ years of software development experience in at least one programming language (Python preferred).
3. 3+ years of experience in one or more ML-specialized domains, such as:
○ speech/audio processing
○ reinforcement learning
○ ML infrastructure / MLOps
○ or other large-scale machine learning domains
4. Strong system design and system architecture abilities for building scalable AI services.
5. Understanding of system administration fundamentals and experience troubleshooting production systems.
6. Solid knowledge of MLOps concepts, including: model lifecycle, inference optimization, monitoring and CI/CD for ML workflows
7. Hands-on experience delivering LLM-based applications such as RAG systems, agent workflows, structured reasoning, or document intelligence.
8. Proficiency with Python and modern AI/ML frameworks (PyTorch, Transformers, LangChain/LangGraph).
9. Experience with cloud platforms, Docker, Kubernetes, or similar infrastructure.
10. Ability to work cross-functionally with various engineering teams.