Aanish W.
Computer Vision & AI Agent | Python - MediaPipe - YOLO Real-Time
Most vision projects fail because of poor-quality data, inaccurate annotations, and weak real-world performance. I've shipped 10+ that didn't. Wrong framework choices. Inference too slow for live video. Models that break the moment lighting, angle, or environment changes. And systems that detect things but can't reason about them or act on them autonomously. That's exactly where most builds stall. I design and build real-time computer vision pipelines that go all the way... from model training to live deployment... and increasingly, from visual perception to autonomous AI agents that understand, decide, and narrate. 𝗪𝗵𝗮𝘁 𝗜 𝗕𝘂𝗶𝗹𝗱 𝗗𝗼𝗰𝘂𝗺𝗲𝗻𝘁 Processing - OCR + LLM extraction from contracts, forms, receipts, scanned PDFs - Document classification & hierarchical taxonomies - Layout analysis & structured data extraction - On-premise RAG over PDF collections 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 - Anthropic , OpenAI, DeepSeek and Chatbot API integrations - Multi-step AI agents & agentic workflows - RAG systems with LangChain & vector databases - Prompt engineering, tool use, function calling 𝗗𝗮𝘁𝗮 𝗣𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀 & 𝗘𝗧𝗟 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀 - Apache Airflow orchestration at 350+ scraper scale - Spark, PySpark, Kafka for streaming & batch - Snowflake, Databricks, AWS Glue, dbt - Multi-tenant ETL with 95%+ success rates 𝗣𝗿𝗼𝗰𝗲𝘀𝘀 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗼𝗻 - n8n, Make, Zapier for end-to-end workflow automation - LLM-powered chatbots (Shopify, Amazon SP-API, HubSpot) - Webhook orchestration & REST API integration - Custom Python automation for repetitive operations 𝗖𝗹𝗼𝘂𝗱 𝗜𝗻𝗳𝗿𝗮𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲 - AWS Lambda, S3, Glue, EC2, Bedrock, Step Functions, ECS - CI/CD pipelines with automated testing & rollback - Docker & Kubernetes for containerized services Domain Expertise: ✅ athlete tracking | shot detection | scoring | drill analysis | pose estimation ✅ defect inspection | PPE compliance | staff monitoring | meter reading | quality control ✅ ANPR | crowd monitoring | people counting | intrusion detection | perimeter security ✅ tumor detection | ultrasound | X-ray/CT analysis | lesion segmentation | medical imaging ✅ aerial monitoring | traffic flow | license plate recognition | vehicle & accident detection ✅ customer analytics | receipt extraction | shelf monitoring | inventory tracking 𝗛𝗼𝘄 𝗜 𝗪𝗼𝗿𝗸 Clear communication, realistic timelines, clean code, and finished products that work in production. Most clients come back; many become long-term partners.
Earnings and projects
Last 6 months ÷ 6
Last 6 months: $565
Billed in all: $1,930$1.9k
$141 in the last 6 months
Across 5 contracts
Across 17 contracts
Earnings, last 30 days
Skill rankings: Top 28% in OpenCV
Ranked by MRR among everyone on Upwork with the skill.
- #50Document AI97 freelancers · 🇵🇰 #17Top 52%🇵🇰#17 of 29
- #61Object Detection & Tracking126 freelancers · 🇵🇰 #26Top 48%🇵🇰#26 of 51
- #75Sports179 freelancers · 🇵🇰 #13Top 42%🇵🇰#13 of 18
- #76OCR Software185 freelancers · 🇵🇰 #12Top 41%🇵🇰#12 of 33
- #254OpenCV912 freelancers · 🇵🇰 #70Top 28%🇵🇰#70 of 202
- #552Civil Engineering1,216 freelancers · 🇵🇰 #86Top 45%🇵🇰#86 of 186
- #785Computer Vision2,498 freelancers · 🇵🇰 #202Top 31%🇵🇰#202 of 624
- #4,240Artificial Intelligence10,593 freelancers · 🇵🇰 #919Top 40%🇵🇰#919 of 2,157