K

Koushik Vasa

About

Detail

Hauppauge, New York, United States

Timeline


work
Job
school
Education
folder
Project

Résumé


Jobs verified_user 0% verified
  • Bridge
    AI/ML Engineer
    Bridge
    Aug 2025 - Current (10 months)
    • Built Bridgette, an agentic AI assistant for a B2B marketplace, replacing a 10+ step workflow (search - filter invite - negotiate) with a single conversational interface. • Designed a multi-step tool-calling agent using Claude (Anthropic API) and DSPy for structured prompt optimization and execution control. • Designed agent decision framework enabling autonomous execution across retrieval, structured queries, and response generation. • Architected production dual-agent system (companies vs. experts) supporting workflows such as expert matching, engagement creation, and earnings analysis via natural language. • Developed 8 production-grade tool schemas with strict runtime validation (Zod), ensuring reliable execution across agent decision
  • Capgemini
    AI Engineer
    Capgemini
    Apr 2021 - Dec 2023 (2 years 9 months)
    • Built document intelligence platform using hybrid RAG (Azure OpenAI + BM25), replacing manual document review for ~ 120 internal users across multiple teams. • Improved retrieval accuracy for enterprise document queries by ~32% by combining dense embeddings with BM25 re-ranking across 500K+ unstructured documents. • Designed LangGraph-based pipelines with clear separation of retrieval, reasoning, and response generation, improving response reliability by ~35%, reducing incomplete and inconsistent outputs in production. • Developed FastAPI inference services handling 200+ concurrent requests with consistent sub-second response times. • Introduced confidence-based validation and context filtering that reduced hallucinated or irrelevant resp
  • C
    Machine Learning Engineer
    CitiusTech Healthcare Technology Pvt. Ltd.
    Aug 2019 - Mar 2021 (1 year 8 months)
    • Built Python/SQL pipelines processing 1M+ patient and claims records, reducing data preparation time by ~30% for downstream ML workflows. • Developed 30-day hospital readmission prediction models using XGBoost and Random Forest, achieving ~82% AUC and enabling early identification of high-risk patients. • Applied PCA and domain-driven feature engineering on clinical and claims data, improving model F1-score by ~12% and reducing feature dimensionality by ~40%. • Resolved recurring pipeline failures including data inconsistencies and job timeouts, reducing failure rates by ~35% while consistently meeting SLA timelines.
Education verified_user 0% verified
  • GEORGE MASON UNIVERSITY
    Master of Science in Computer Science (Machine Learning)
    GEORGE MASON UNIVERSITY
    Jan 2024 - Dec 2025 (2 years)
    GPA 3.87
Projects (professional or personal) verified_user 0% verified
  • NA
    MediConnect: AI-Powered Healthcare Matching Platform
    NA
    Jan 2025 - Current (1 year 5 months)
    • Built and deployed AI-powered patient-to-doctor matching platform using 2.8M+ CMS clinician records, enabling real-time symptom-based specialist discovery • Designed Gemini 2.5 Flash-based recommendation engine with confidence scoring and fallback handling for ambiguous inputs • Developed multi-factor compatibility scoring system ranking doctors based on symptoms, geolocation, and predicted consultation cost • Built conversational AI assistant supporting structured intake, image uploads, and contextual diagnostic guidance • Implemented Node.js + Express APIs (5 endpoints) powering search, ranking, and recommendation workflows • Designed interactive frontend with OpenStreetMap-based distance calculations and 3D anatomy explorer (Three.js)
  • NA
    CitationSleuth: RAG-Based Fact Verification System
    NA
    Jan 2024 - Current (2 years 5 months)
    • Built dual-layer LLM validation system combining semantic retrieval and Neo4j graph traversal to verify generated claims • Improved verification precision by linking embedding-based evidence retrieval with graph-based relationship validation • Developed real-time interface surfacing low-confidence or unsupported outputs before downstream usage
  • NA
    ClearCare: AI-Powered Clinical Data Pipeline
    NA
    Jan 2023 - Current (3 years 5 months)
    • Built end-to-end pipeline ingesting structured EHR and unstructured clinical notes, normalizing data for downstream ML and analytics workflows • Automated validation and transformation in Python, reducing manual preprocessing effort and recurring data quality issues • Integrated LLM-based entity extraction to standardize clinical terminology, improving consistency of training datasets