Job Description:
- Own the architecture, development, and productionization of core AI data product capabilities, including natural language to SQL, dashboard generation, and insight / report generation.
- Build production-grade LLM application pipelines for enterprise data scenarios, including:
- metadata and schema retrieval
- semantic layer and metric understanding
- query planning and SQL generation
- SQL validation, rewriting, and execution
- visualization spec generation
- narrative insight generation
- Design and implement reliable backend services and platform capabilities that balance accuracy, access control, explainability, observability, latency, and cost.
- Deeply understand user workflows in analytics and data consumption, and translate ambiguous business questions into scalable, reusable engineering systems.
- Work closely with Data Infra, Data Engineering, BI, Frontend, Design, and AI / ML engineering teams to deliver products from zero to one and scale them from one to many.
- Establish and continuously improve the LLM evaluation and feedback loop, including offline benchmarks, online metrics, user feedback, prompt / model versioning, failure analysis, and quality improvement.
- Drive performance, reliability, and engineering excellence across the system, and contribute to long-term architectural evolution.
- Stay current with best practices in LLM applications, AI agents, semantic analytics, and enterprise AI systems, and turn them into practical production solutions.
Requirements:
- Bachelor's Degree or above in Computer Science, Software Engineering, Data Engineering, or related fields.
- Minimum 6 years of experience in backend engineering, platform engineering, data infrastructure, or AI application engineering, with the ability to own complex system design and core module delivery.
- Strong computer science fundamentals, including data structures and algorithms, operating systems, networking, databases, and distributed systems.
- Proficient in at least one backend language such as Go, Java, or Python.
- Strong hands-on experience building LLM-powered applications, with solid understanding of Prompt Engineering, RAG, Tool Calling, Agents, evaluation frameworks, inference optimization, and guardrails.
- Strong understanding of data and analytics products, including SQL, data modeling, data warehouses / lakehouses, OLAP systems, semantic layers, metrics systems, dashboards, and reporting.
- Familiarity with one or more enterprise data / big data technologies such as Spark, Flink, Kafka, Trino / Presto, StarRocks, ClickHouse, Hive, or similar systems.
- Strong problem-solving and abstraction skills, with the ability to convert ambiguous requirements into robust and extensible technical designs.
- Strong product sense and user empathy able to think beyond model capability and understand end-to-end user workflows.
- Strong communication and cross-functional collaboration skills.
[Preferred Qualifications]
- Experience building production-grade Text-to-SQL, AI Copilot, AI BI, analytics assistants, or automated dashboard / report / insight generation systems.
- Experience building large-scale internal data platforms, self-service analytics platforms, or enterprise data products.
- Experience in leading internet companies on AI-related initiatives, and additional experience in foundation model or AI-native product companies.
- Familiarity with semantic layers, metrics layers, data governance, query security, grounding, explainability, and citation / traceability mechanisms for trustworthy analytics.
- Domain experience in e-commerce, ads, search, recommendation, risk, or business analytics.
- Strong technical leadership with the ability to drive architecture decisions and raise engineering standards across the team.
