.png){kind=logo}
Xicheng Liang
Intern AI/Full-Stack Engineer specializing in backend systems and applied machine learning
Connect with Xicheng
Xicheng 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 shipped a production agentic RAG system for healthcare analysts that automated compliance/operations knowledge retrieval across PDFs, reports, and databases. Emphasizes production reliability (monitoring, retries, fallbacks, async queues), strong evaluation/iteration loops, and measurable impact (3–10s responses and ~98% top-k retrieval accuracy).
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 LLM agentic RAG system with reliability features (caching, monitoring, retries, fallbacks)
- Reduced knowledge-query turnaround from minutes to ~3–10 seconds
- Achieved ~98% top-k retrieval accuracy
- Designed predictable multi-step agent pipeline (query understanding → retrieval → reranking → self-correction → citations → generation)
- Improved answer quality by adding a re-ranker after evals showed weak/irrelevant chunk usage
- Stabilized latency and behavior under traffic spikes using caching and async queues
- Improved tool-calling consistency via narrowed tool choices, strict schemas, and deterministic backend fallbacks
- Handled messy operational data with strict schema validation, normalization, and idempotent/retry-safe processing
Like what you see? We'll introduce you to Xicheng directly.
Experience
Education
Languages
Browse Similar
Similar Candidates
Narasimha Jwalapuram
Mid-level Applied AI Engineer specializing in LLM agents, RAG, and model alignment
“Applied Scientist with legal-tech experience who builds production LLM systems. Created and deployed Quibo AI, a LangGraph-based multi-agent pipeline that turns large markdown/Jupyter inputs into polished blogs and social posts, overcoming context limits via ChromaDB + HyDE RAG. Also built a large-scale iterative code-evolution workflow using multi-model orchestration (GPT/Claude/Gemini) with testing, debugging loops, and evaluation/observability practices.”
Mid-level AI Engineer specializing in LLM agents, RAG, and enterprise GenAI
Sayuj Shah
Mid-level Data Analyst & AI Practitioner specializing in ML, LLMs, and analytics platforms
“Data Analyst at U.S. Cellular who built production LLM solutions, including a Tableau-embedded chatbot that converts natural language questions into Oracle SQL and returns actionable KPI insights for non-technical users. Also authored MAD-CTI, a multi-agent LLM system for dark web hacker forum threat intelligence (published in IEEE Access) that outperformed single-agent approaches by 14%.”
Junior AI Engineer specializing in LLM systems, RAG pipelines, and cloud microservices
Interested in Xicheng?
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 Xicheng
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent