.png){kind=logo}
Xinyuan Lin
Intern Software Engineer specializing in LLMs, RAG, and full-stack systems
Connect with Xinyuan
Xinyuan already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Built and productionized a multi-agent LLM analytics assistant at eBay that routes natural-language questions to retrieval or text-to-SQL, dynamically retrieves relevant schemas via a vector DB, and executes against a data warehouse. Drove a major quality lift (text-to-SQL accuracy 60%→85%) and materially reduced time engineers/PMs spent getting data insights through strong eval/monitoring, tracing, and reliability-focused design (schema retrieval, strict JSON outputs, retries/clarifications).
Find your next great hire
Our AI agents source, screen, and vet candidates for your open roles. Get qualified candidates within 48 hours.
Key Strengths
- Shipped production multi-agent LLM system for internal analytics at eBay
- Improved text-to-SQL accuracy from 60% to 85%
- Designed router-based orchestration with deterministic structured outputs (strict JSON schemas)
- Built robust evaluation framework using curated real user queries (SQL correctness, execution success, intent match)
- Implemented reliability features: schema pruning/retrieval, clarification loops, retries for invalid SQL
- Production monitoring and debugging via detailed tracing; detected issues like infinite loops
- Reduced hallucinated joins by limiting schema context to relevant tables
Like what you see? We'll introduce you to Xinyuan directly.
Experience
Education
Languages
Browse Similar
Similar Candidates
Senior Full-Stack Software Engineer specializing in cloud-native distributed systems and AI
Senior AI/ML Engineer specializing in applied AI and scalable backend systems
Aditya Testapplicant
Senior Full-Stack Software Engineer specializing in cloud, AI, and distributed systems
“Built Reval as a full-stack product/company, using a Next.js frontend with Java Spring and Python FastAPI backends, including AI-driven workflows powered by frontier models. Has hands-on experience improving search UX and relevance with a KNN-based people search, and emphasizes heavy testing and dataset iteration to manage LLM nondeterminism.”
Staff-level Software Engineer specializing in LLM inference infrastructure and scalable model serving
Senior Full-Stack Engineer specializing in AI/ML platforms and cloud-native systems
Russell Wong
Senior Software Engineer specializing in large-scale backend reliability and media platforms
“Backend/data engineer with experience on large-scale consumer platforms (Google and Meta), building high-traffic Python microservices (REST/gRPC) on Kubernetes with strong reliability/observability practices. Delivered AWS container-based deployments with CI/CD and IaC, and built AWS Glue ETL pipelines on S3 with schema evolution and data quality controls; also has demonstrated SQL tuning impact (15% latency reduction) and incident ownership for batch pipelines.”
Interested in Xinyuan?
We'll personally introduce you - no strings attached.
Build your dream team with Reval
Our AI agents source, screen, and vet candidates for your open roles. Get qualified, high-intent candidates on your desk within 48 hours.
Discover more candidates like Xinyuan
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent