Jatin A. Salve

Machine Learning Engineer building visual search, personalization, and responsible AI systems.

assets/img/prof_pic.jpg

Gainesville, FL

jatin.salve@ufl.edu

resume · projects

M.S. Computer Science · University of Florida

Production ML for search, ranking, and trustworthy multimodal AI.

I’m Jatin Salve, a machine learning engineer and researcher focused on computer vision, visual retrieval, recommender systems, generative AI, and responsible AI evaluation. I like systems where model quality, latency, reliability, and product impact are measured together.

1M+ daily production ML requests
21% NDCG@10 lift in multimodal retrieval
9% CTR lift from ranking improvements
ACL 2024 publication, 2026 submission

What I Build

  • Visual search & multimodal retrieval: dense embeddings, FAISS / ANN indexing, learned reranking, evaluation pipelines.
  • Recommendation & personalization systems: user understanding, segmentation, sequence modeling, A/B-tested production deployment.
  • Responsible generative AI: RAG, claim-level verification, faithfulness checks, safety evaluation, hallucination reduction.
  • ML infrastructure: Ray Serve, FastAPI, Docker, Kubernetes, AWS ECS/S3/Lambda, GPU batching, CI/CD.

Selected Work

  • Built multimodal retrieval pipelines combining visual and textual signals, improving NDCG@10 by 21% with dense transformer embeddings and reranking.
  • Shipped recommendation and ranking systems at ICICI Bank serving 1M+ daily requests, delivering a 9% CTR lift and 12% relevance improvement.
  • Developed responsible AI evaluation harnesses for context grounding, faithfulness, safety, and claim-level verification.
  • Published multimodal clinical summarization work at ACL 2024, with structured medical QA work submitted to an ACL 2026 workshop.

Availability

Available September 21 - December 11, 2026 for full-time ML internship work in San Francisco, Palo Alto, Seattle, New York, or remote.

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

  1. 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
  2. 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