Work Experience
Software Developer @ IBM Canada Ltd (Apr 2025 - Present)
- Distributed LLMs Inference Backend API Development and Infrastructure Autoscaling (vLLM, Kubernetes, KServe, HPA, KEDA)
- Scheduling and Autoscaling Algorithms, Optimized Batch Processing (Queueing Theory), e.g., inference workload-based prefix-EDF
AI Research Engineer @ Instavision Inc (Nov 2023 - Feb 2025)
- Data Engineering, Model Training & Tuning (Vision, Text, Vision-Text Embedding Models), Vector Embedding Search, Prompt Engineering
- Computer Vision Systems: Object Detection and Face Recognition in Distributed Environments
- Low-Latency Object Recognition for Security Cameras, Face Recognition (YOLOv7, GPT-4o, Qdrant DB, ONNX, Redis, GO)
AI Research Intern @ National Bank of Canada (Sept 2023 - Aug 2024)
- Conversational Question Answering, Knowledge Graphs, Chatbots, LLMs
- Built JIRA Issues Chatbot for Question Answering, Executive Summaries, and Dependency Analysis
Software Engineer @ Infosys (Aug 2021 - Aug 2022)
- Backend API Development and NLP Pipelines (Flask, Python, RASA)
- Developed NLP Pipeline for Natural Language to Database Query Transformation (BERT Fine-Tuning) and API Development
📚 Publications & Research Work (prev @ CoDS.ai)
Education
Concordia University, QC, CA --- Master of Science (Computer Science)
Gujarat Technological University, IN --- Bachelor of Engineering (Computer Engineering)