.png){kind=logo}
Muhan Zhang
Junior AI Software Engineer specializing in LLM pipelines, OCR, and RAG
Connect with Muhan
Muhan 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 LLM pipeline for nursing home Medicare reimbursement (PDF OCR + fact extraction + keyword RAG + QA) that reportedly increased payouts by ~$1K/month per patient. Strong in LLM ops/benchmarking (ground truth, LLM-as-judge, cost/I-O tracking) and pragmatic optimization—swapped retrieval approaches, fine-tuned a small model to cut OCR cost 90%, and migrated workloads to Azure/Temporal to scale nightly processing 10x.
Experience
Education
Key Strengths
- Deployed LLM system that increased Medicare reimbursement by ~$1,000/month per patient for nursing home facilities
- Reduced OCR costs ~90% by distilling data and fine-tuning a 2B model and self-hosting
- Cut QA inference cost ~10x by benchmarking prompts/models and switching from GPT-4.1 to Grok-4-fast-reasoning with minor prompt changes
- Built LLM infra for prompt/model benchmarking with ground-truth labeling, prompt versioning, and cost/I-O observability
- Improved throughput ~10x by migrating pipeline tasks to Azure Container Apps Jobs
- Designed robust Temporal workflows with retries, reset points, and operational visibility for nightly ingestion pipelines
- Effective collaboration with non-technical SMEs; translates output issues into upstream retrieval/pipeline fixes
Discover more candidates like Muhan
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent