Jatin A. Salve

Gainesville, FL

University of Florida · M.S. Computer Science

I build ML systems where retrieval quality, latency, and trust are measured together.

I’m Jatin Salve. My work sits around visual search, recommendation systems, multimodal retrieval, and responsible AI evaluation. I’m most interested in the point where a model stops being a demo and becomes something people can measure, debug, and rely on.

Selected work Resume Email me

Production ranking

Shipped personalization and recommendation workflows at ICICI Bank serving 1M+ daily requests.

Retrieval evaluation

Improved multimodal retrieval NDCG@10 by 21% with dense embeddings, FAISS search, and reranking.

Responsible AI

Built claim-level verification and grounding checks for medical QA and generative AI systems.

What I’m working on

Visual and multimodal retrieval: embedding pipelines, ANN indexing, reranking, and retrieval diagnostics.
Recommendation systems: user understanding, segmentation, ranking experiments, and A/B-tested deployment.
Faithful generation: RAG, RDF grounding, claim verification, and evaluation harnesses for hallucination reduction.
ML serving: Ray Serve, FastAPI, Docker, AWS ECS, batching, CI/CD, and latency measurement.

Availability

I’m looking for full-time ML internship work from September 21 to December 11, 2026, especially in visual search, recommender systems, multimodal retrieval, or responsible AI.

news

Jan 15, 2026	Submitted structured medical QA work to the ACL 2026 SURGeLLM workshop, focusing on RDF retrieval, claim-level verification, and faithful generative AI evaluation.
Dec 01, 2025	Started research assistant work at the University of Florida on computer vision, multimodal retrieval, responsible AI evaluation, and agentic ML systems.
Aug 15, 2024	Published “From Sights to Insights: Towards Summarization of Multimodal Clinical Documents” at ACL 2024, with contributions to the vision cross-attention fusion module and grounding ablations.

selected publications

ACL
From Sights to Insights: Towards Summarization of Multimodal Clinical Documents

Soumya Ghosh, Mohit Tomar, Anshul Tiwari, and 3 more authors

In Proceedings of the 62nd Annual Meeting of the Association for Computational LinguisticsACL 2024 long paper, main conference. , Aug 2024

Abs Bib

Multimodal clinical document summarization work focused on grounding generated summaries in visual and textual evidence. Contribution: designed the vision cross-attention fusion module and ran ablation studies isolating the contribution of multimodal grounding.
@inproceedings{ghosh2024sights, title = {From Sights to Insights: Towards Summarization of Multimodal Clinical Documents}, author = {Ghosh, Soumya and Tomar, Mohit and Tiwari, Anshul and Saha, Sriparna and Salve, Jatin Avinash and Sinha, Manjira}, booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics}, year = {2024}, month = aug, publisher = {Association for Computational Linguistics,}, }
ACL
Structure-Grounded Medical QA: RDF Retrieval and Claim-Level Verification for Faithful Answering

Stocks Natalias, Jatin Avinash Salve, Hunter, and 5 more authors

ACL 2026 Workshop on Structured Understanding and Reasoning for Generative LLMs (SURGeLLM), Aug 2026

Submitted

Abs Bib

Structured medical question answering work combining RDF retrieval with claim-level verification for faithful generative AI outputs. Contribution: proposed claim-level verification as the core faithfulness mechanism, designed the structured retrieval pipeline, and led evaluation design.
@article{natalias2026structure, title = {Structure-Grounded Medical QA: RDF Retrieval and Claim-Level Verification for Faithful Answering}, author = {Natalias, Stocks and Salve, Jatin Avinash and Hunter and Kunchepu and Herrera and Youm and Gilda and Dorr}, journal = {ACL 2026 Workshop on Structured Understanding and Reasoning for Generative LLMs (SURGeLLM)}, year = {2026}, note = {Submitted} }