Upwork home
Sign up
Project Catalog
DesignDesign
Video & AudioVideo & Audio
Development & ITDevelopment & IT
MarketingMarketing
Writing & TranslationWriting & Translation
MoreMore

You will get a complex data extraction and transformation assessment

Yu-Ting L.Status: Offline
Yu-Ting L.
Preview image

Let a pro handle the details

Buy Generative AI services from Yu-Ting, priced and ready to go.
Yu-Ting L.Status: Offline
Yu-Ting L.
Preview image

Let a pro handle the details

Buy Generative AI services from Yu-Ting, priced and ready to go.

Project details

Turn inconsistent OCR and document extraction into a measurable improvement plan. I will test representative PDFs, scans, Office files, spreadsheets, tables, and mixed layouts to identify failures in OCR quality, structure recovery, chunking, metadata, source anchors, retrieval readiness, latency, and cost. You receive reproducible findings, prioritized failure categories, evaluation recommendations, and an implementation-ready plan. Advanced adds deeper multimodal architecture guidance for difficult layouts, tables, and citation-grade provenance. I work async-first with clear written updates and can assess Python pipelines using OCR engines, vision-language models, vector databases, and custom ingestion services.
AI Algorithms
Multimodal Large Language Model, Transformer Model
AI Applications
AI-Enhanced Classification, Image Analysis, Image Processing, Natural Language Understanding, Text Recognition
AI Development Language
Python
AI Tools
Hugging Face
What's included
Service Tiers Starter
$250
Standard
$550
Advanced
$950
Delivery Time 4 days 7 days 10 days
Number of Revisions
122
AI Model Integration
-
-
-
Batch Normalization
-
-
-
Database Integration
-
-
-
Detailed Code Comments
-
-
-
Image Upscaling
-
-
-
MLOps
-
-
-
Model Deployment
-
-
-
Model Documentation
-
-
-
Model Monitoring
-
-
-
Model Testing & Optimization
-
-
-
Model Tuning
-
-
-
Natural Language Processing
-
-
-
NLP Tokenization
-
-
-
Pre-Training
-
-
-
Prompt Engineering
-
-
-
Setup File
-
-
-
Source Code
-
-
-

Frequently asked questions

Yu-Ting L.Status: Offline

About Yu-Ting

Yu-Ting L.Status: Offline
AI Systems Engineer | Complex Data, Retrieval & Agentic Workflows
Taipei, Taiwan - 1:53 pm local time
I build production AI systems that transform complex, heterogeneous data into reliable structured information and precise, evidence-grounded retrieval. My work covers data ingestion and transformation, hybrid retrieval and reranking, retrieval evaluation, and agentic workflows with tool use, validation, observability, and human review.

I also build the platform around these systems: PostgreSQL data models, APIs, background jobs, access control, usage metering, billing and payment flows, and failure recovery. Technologies such as FastAPI, Supabase, Stripe, OCR, and VLMs are implementation choices selected according to the project—not my professional positioning.

I have worked in AI engineering and research since 2021. Since January 2024, I have led product engineering and research at Apertis AI, where I build:

• Verbatim: multimodal ingestion for PDF, Office documents, and OCR; hybrid Qdrant and lexical retrieval; reranking; source citations; and evaluation.
• Production AI infrastructure: multi-model routing, provider failover, usage metering, cost controls, Stripe billing, authentication/RLS, and APIs.
• Reliable agent workflows: tool calling, structured outputs, validation, retries, observability, and human review.
• Open-source AI: merged contributions to LlamaIndex, Vercel AI SDK, Kilo Code, Lightning AI’s lit-llama, Lobe Icons, and CAG across Python and TypeScript ecosystems.

Core stack:
Python, FastAPI, Go, PostgreSQL, Supabase, Qdrant, BM25S, Redis, React, TypeScript, Next.js, Docker, and OpenAI/Anthropic APIs.

Best-fit projects:
• RAG quality, retrieval, citation, or evaluation improvements
• Document parsing, OCR, and multimodal ingestion
• AI agents, tool integrations, and backend reliability
• Complete AI SaaS features from API to UI
• LLM routing, metering, billing, and observability

Research credentials:
I am the first author of a CIKM 2022 paper and a recent preprint on retrieval bottlenecks in multi-hop document question answering. I have served on the LREC 2026 Scientific Committee and as a program committee member or reviewer for ROCLING, LREC-COLING, and COLING.

I work async-first, communicate through clear written updates, and provide reproducible deliverables. I am available up to 50 hours per week. Scheduled calls are possible between 9:00 PM and 12:00 AM Taiwan time (UTC+8).

Steps for completing your project

After purchasing the project, send requirements so Yu-Ting can start the project.

Delivery time starts when Yu-Ting receives requirements from you.

Yu-Ting works on your project following the steps below.

Revisions may occur after the delivery date.

Review samples and success criteria

I review representative files, expected outputs, constraints, and measurable acceptance criteria.

Map the current extraction pipeline

I map OCR, parsing, structure recovery, chunking, metadata, storage, and downstream retrieval dependencies.

Review the work, release payment, and leave feedback to Yu-Ting.