Jan 2024 – Present · 2 yrs 4 mos · India · On-site

• As of 2026, Elucidata has raised about $23M, including a $16M Series A led by Eight Roads, with participation from F-Prime, IvyCap, and Hyperplane. Customers include Pfizer, Boehringer Ingelheim, Janssen, Genentech, Visterra, and Eli Lilly. We turn raw biomedical assets into AI-ready data by uniting omics, clinical, and imaging sources so R&D moves faster.
• I lead GenAI and step in when the problem is “we’ve tried everything.” I ship production systems under pressure across data, LLMs, and biomedical R&D.
• Right now I’m building Ultra Deep Research to cut preclinical timelines from years to weeks. In parallel, I’m solving biomedical data findability with an LLM-powered search across open-access PubMed (full text plus supplements), GEO, ArrayExpress, PRIDE, ClinicalTrials.gov, and 8+ other sources.
• I built a multi-agent curation engine that ingests messy biomedical documents, generates schemas, extracts fields, and normalizes to controlled ontologies. It delivers ~98% field-level accuracy and up to 500× faster throughput than manual curation.
• I co-authored “Multi-agent AI System for High-Quality Metadata Curation at Scale,” outlining the system and benchmarks for scalable, high-quality biomedical metadata curation.
• I also co-authored “Oncopacket: Integration of Cancer Research Data Using GA4GH Phenopackets” with NCI and Lawrence Berkeley National Laboratory. We open-sourced the code and released Phenopackets for 23,650 individuals across 12 cancer types to enable standards-based downstream AI/ML analysis.
• I won 1st place (multimodal AI/ML) with a three-person team in NCI’s CRDC AI Data Readiness Challenge, earning $20,000. Our model separates primary tumor from normal solid tissue in lung squamous cell carcinoma at ~95% accuracy with strong class-imbalance handling.
• Before this, I built the core biomedical knowledge graph, search infrastructure, and open-source fine-tuning infrastructure, among other systems.

Jan 2023 – Dec 2023 · 11 mos · India · On-site

• Earlier, as a Data Scientist, I turned biomedical curation into production automation. I built agentic RAG systems that cut hours to minutes, and an ontology-normalization engine that maps entities to the right ontology at ~99% accuracy.
• I built the pipelines that became core product infrastructure. RNA-seq scaled to 40,000 GEO datasets, cut processing from ~90 minutes to ~7, and hit 96% disease accuracy. Proteomics collapsed 24–28 GDC/PDC tables into one schema, cut processing from ~2 hours to ~9 minutes, and launched a new offering.
• I also shipped what customers could feel. I co-created PollyGPT for natural-language multi-omics analysis, ran GenAI demos for 27 industry leaders, and drove unstructured-to-structured automation across biotech, materials science, IND filings, and Ayurveda. It produced 11 PoCs, supported 17 sales calls, and raised client acceptance to 65%.

Jul 2022 – Dec 2022 · 5 mos · India · On-site

• As a Data Analyst, I built production systems that replaced manual work across modeling, knowledge access, client delivery, and ops.
• For patient-specific anti-cancer drug selection (169 drugs), I rebuilt the random-forest pipeline and engineered 21 biology-driven features (DoRothEA, MSigDB, GSVA). Outcome: +35% accuracy over baseline, and training time cut from 1,270 hours to 40 using HPC, parallelism, and GPU acceleration.
• I built our internal, self-hosted AI assistant from scratch. It indexed Confluence and internal repos with permission-aware retrieval, answered with cited sources, and ran a 24/7 support agent that opened context-rich Jira tickets. I also automated delivery tracking into a live Jira dashboard with Slack alerts, turning weekly status churn into real-time visibility.
• For multiple major U.S. pharma clients, I shipped an AI harmonization agent that understood messy column variants, proposed the right mappings, and standardized files with minimal review. It replaced a multi-person weekly workflow, earned a perfect NPS, and ran for years with near-zero support.
• That foundation set up my later Data Scientist and Senior Data Scientist roles, where I carried the same mindset into agentic pipelines and GenAI at enterprise scale.