AI Field Engineer

Job Description

1. Scenario-Driven Application Development

• Deeply understand enterprise business scenarios, identify core pain points, and translate them into technical solutions. You will lead the design and development of scenario-specific AI applications, such as intelligent risk control systems, data insight assistants, and more.

2. Understanding Core Architectures of AI Applications. Develop a solid understanding of the following AI application architectural components:

• Conversational & Task Frameworks: Build LLM-based conversational engines and agent frameworks capable of autonomously executing complex data tasks.
• RAG Engine Optimization: Design and implement efficient, accurate Retrieval-Augmented Generation (RAG) systems with deep integration of structured and unstructured data.
• Data-Driven Insight Tools: Develop intelligent analysis tools that automatically detect data patterns, anomalies, and trends.

3. Engineering Excellence & ProductizationDrive the process from technology selection and PoC development to full productization. Work closely with product, algorithm, and platform teams to transform technical vision into reliable, user-delighting products.

Requirements

1. Strong Computer Science Fundamentals: Solid understanding of data structures, algorithms, operating systems, and networks. Proficient in at least one mainstream programming language (Python/Java/C++/Go).
2. Experience in Combining Data & AI: Knowledge of machine learning or LLM fundamentals, plus hands-on experience integrating them with modern data tech stacks (e.g., Spark, Flink, Trino, Doris).
3. Understanding of the AI Application Tech Stack: Familiarity with at least two of the following, with hands-on implementation experience:
4. LLM application development, including prompt engineering and fine-tuning
5. Search systems (ElasticSearch, Vector DBs) and RAG architectures
6. Agent frameworks (LangChain, LlamaIndex) or custom task-planning engines
7. Product & User-Centric Mindset: Passionate about creating user value. Able to zoom out from technical implementation and shape product experience from the user’s perspective. Measure technical success by product outcomes.
8. Learning & Communication Skills: Ability to learn continuously in a fast-evolving field. Excellent communication skills to articulate complex technical concepts and collaborate across teams.

Nice-to-Have

1. AI application development experience in industries such as finance, insurance, or retail
2. Experience with MLOps or DataOps, including model deployment, monitoring, and iteration- Contributions to open
3. source communities or active technical blogging