Rajdeep Mondal

Co-Founder

Bengaluru, Karnataka, India5 yrs 4 mos experience
Most Likely To SwitchAI Enabled

Key Highlights

  • Led development of multi-agent AI systems for biomedical data curation.
  • Achieved 95% accuracy in tumor classification using AI.
  • Built production systems that significantly reduced processing times.
Stackforce AI infers this person is a Healthcare AI Specialist with expertise in data science and machine learning.

Contact

Skills

Core Skills

Generative AiMachine LearningData Science LeadershipData ScienceMachine Learning OptimizationPredictive ModelingApplied Machine LearningNatural Language Processing (nlp)Data AutomationData AnalysisData QualityData Cleaning

Other Skills

Large Language Models (LLM)Biomedical Data ManagementScikit-LearnTensorFlowBig DataPandas (Software)R (Programming Language)Data VisualizationAutomationBioinformatics WorkflowsRShinyAI Software DevelopmentAI Chatbot DevelopmentAutomation SolutionsBioinformatics

About

In Build Mode.

Experience

5 yrs 4 mos
Total Experience
2 yrs 8 mos
Average Tenure
3 yrs 8 mos
Current Experience

Elucidata

3 roles

Senior Data Scientist

Promoted

Jan 2024Present · 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.
Generative AIMachine Learning

Data Scientist

Promoted

Jan 2023Dec 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%.
Generative AIApplied Machine Learning

Data Analyst

Jul 2022Dec 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.
Machine Learning OptimizationData Analysis

Various startups

Founder

Nov 2020Jul 2022 · 1 yr 8 mos · India · On-site

  • Between 2021 and 2022, I chased three startup ideas and failed at all of them. One was an AI voice-dubbing system, like what ElevenLabs does today, except I tried to build it in 2020 with almost nothing: a maxed-out credit card and a hard cap on compute. The goal was simple: take lectures from MIT OpenCourseWare, Stanford, and others, and make them available in Indian languages like Hindi and Bengali, with the speaker’s voice actually speaking the language, not just subtitles.
  • I cold-reached out to schools and found early distribution. Three regional schools and two regional colleges agreed to try it, and I got content in front of students. It didn’t become a business, but it forced me to learn deep learning by building, and MLOps by shipping and maintaining a system under real constraints.
  • Those failures taught me more than any degree could. It was months of experiments, dead ends, and hard lessons.
  • That stretch pulled me into this field and set me up for what came next.

Education

University of Calcutta

BS Honours — Computer Science

Jan 2017Oct 2020

Stackforce found 100+ more professionals with Generative Ai & Machine Learning

Explore similar profiles based on matching skills and experience