Harsh Kumar

Harsh Kumar

About

Detail

AI / Software Engineer · Production LLM Pipelines · Geospatial · Klarety (founding)
India
Contact Harsh regarding: 
work
Full-time jobs

Timeline

work
Job
school
Education
folder
Project
flag
Award

Résumé

Jobs verified_user 0% verified
  • Klarety
    SDE 2
    Klarety
    Oct 2024 - Current (2 years 1 month)
    • LLM Development: Designed and implemented an advanced LLM system for a geospatial assistant, including rolling context summarization, semantic relevance filtering with Sentence Transformers, and token-aware memory management—improved query correlation by 60% thus reduced hallucinations.
    • Developed a high-performance raster and vector tiling server with full CRUD operation support, capable of handling millions of requests per minute; optimized for superior efficiency and scalability reducing latency by 50% in high-volume geospatial data visualization and database load by 90% through PMTiles integration.
    • custom XYZ tile server: Created a custom XYZ tile server with FastAPI and Rust(Martin) for scalable visualization of raster/v
  • Aidash
    Software Engineer
    Aidash
    Oct 2022 - Oct 2024 (2 years 1 month)
    • Improved existing SaaS services by leveraging PostGIS and Python, enhancing the system by approximately 80%, and assisting the organization in securing a million-dollar contract.
    • Coordinate with leadership team and implement new feature request in SaaS.
    • Dockerized and built CI/CD to deploy production code.
    • Develop and maintain data driven large scale SaaS services.
    • Developed microservices for seamless integration of a SAAS product with third-party services to enhance traction.
    • Mentored and lead onboarding of new hires for SAAS product.
    • Own and ensure alignment of the team learning programs for all members.
  • Soroco
    Software Engineer
    Soroco
    Jun 2021 - Oct 2022 (1 year 5 months)
    • Microservices Integration: Designed and deployed scalable microservices architecture, enhancing system reliability and enabling integration of diverse technology stacks.
    • End-to-End Development: Led the full lifecycle of REST API development, from design to deployment, tailored to meet complex business needs.
    • Fault Detection System: Collaborated with product teams to develop a fault detection module for the Scout product, reducing operational downtime by 45%
    • Agile Methodology: Championed Agile methodologies, resulting in a 25% improvement in project delivery timelines.
  • SirpiDataScience
    Full Stack intern
    SirpiDataScience
    Aug 2020 - Jun 2021 (11 months)
    • Dashboard Development: Created interactive dashboards using Shiny and React, enabling data-driven decision-making for key stakeholders.
    • API Integration: Developed and integrated APIs to seamlessly connect front-end applications with backend services.
    • Code Optimization: Improved code efficiency by 30% through parallel processing techniques, enhancing overall system performance.
    • Automation Scripting: Automated repetitive tasks using Python scripts, reducing manual workload by 40%.
  • K
    Back End Developer intern
    KaliberAI
    Jun 2019 - Jul 2019 (2 months)
    • Detect different of artifact in medical image.
    • Analyze different computer vision algorithm on different data-sets.
    • Write test script to automate task in python.
  • IIT Guwahati
    Former intern at IIT Guwahati
    IIT Guwahati
    Dec 2018 - Jan 2019 (2 months)
    • Web Interface Development: Built and integrated an online automatic speech recognition module into a web interface, enhancing accessibility.
    • Frontend development: Build React dashboard for interactive user experience.
Education verified_user 0% verified
  • Tezpur University
    BTech - Bachelor of Technology, Computer Software Engineering
    Tezpur University
    Jan 2017 - Dec 2021 (5 years)
Projects (professional or personal) verified_user 0% verified
  • E
    Endoscopy-artifact-detection
    Jun 2019 - Jul 2019 (2 months)
    It was my Summer internship work to detect different type of artifact in endoscopy images, it was based on EAD2019 challenge.
  • C
    Compression_Artifact
    Jun 2019 - Jul 2019 (2 months)
    My task was to remove compression artifact in an image, For this purpose i have used ARCNN(Artifacts Reduction CNN) architecture ARCNN is used to reduce the Blocking Artifacts, Ringing Artifacts and Blurring.
  • E
    Easy_data_sharing_using_raspberry_pi
    My project is a device which can convert any normal(Wired) hard drive to wifi enabled hard drive.
Awards verified_user 0% verified
  • IIT Guwahati
    Tech-Expo
    IIT Guwahati
    Aug 2018
    Achieved 3rd prize from IIT Guwahati in Competition Techniche “Tech Expo 2018” for a project, among 50 students in senior category (National level competition).
  • Tezpur University
    B-idea
    Tezpur University
    Achieved 3rd prize in Business idea competition ‘B-idea’, organized by Tezpur University. It was a startup competition on national level.