Parag Dharap
@paragdharap
I build evaluation-driven LLM, agentic AI, and backend systems that improve customer workflows.
What I'm looking for
At Wizeline, I design LLM-powered proofs of concept, RAG pipelines, and automated evaluation loops for customer data and marketing workflows. My Pinecone-backed RAG work improved answer relevance by 30% in internal benchmarking.
Previously at Sardine, I architected agentic AI systems combining LLM reasoning and deterministic rules, reducing manual fraud-review workload by 25% in pilot deployments. I also built document-understanding pipelines that improved unstructured-data extraction accuracy by 35%.
My background includes probabilistic clinical-risk models at Arine and scalable cloud backend services at Microsoft. I ground AI experimentation in measurable customer outcomes, production evaluation, and reliable Python-based services.
Experience
Work history, roles, and key accomplishments
Designed and developed LLM-powered proof-of-concept systems using LangChain and prompt engineering, validating generative AI applications for customer data and marketing workflows. Built RAG pipelines with Pinecone, improving answer relevance by 30%, and implemented automated LLM evaluation pipelines with LLM-as-a-judge.
Education
Degrees, certifications, and relevant coursework
The University of Texas at Dallas
Bachelor of Science, Computer Science
2008 - 2012
Bachelor's Degree in Computer Science from The University of Texas at Dallas, completed in 2012.
Tech stack
Software and tools used professionally
Availability
Location
Authorized to work in
Salary expectations
Job categories
Skills
Interested in hiring Parag?
You can contact Parag and 90k+ other talented remote workers on Himalayas.
Message ParagGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
