I am a AI/ML Engineer and Full-Stack Developer focused on shipping production AI systems. With an MS in Machine Learning from George Mason University and hands-on experience building RAG pipelines, LLM agents, and scalable AI infrastructure, I specialize in turning research-grade models into reliable, user-facing applications.
My work spans the full stack — from embedding pipelines and prompt orchestration to React frontends and FastAPI backends. I have built and deployed multi-agent systems, fact-checking RAG architectures, and AI-powered platforms handling millions of provider records, always with a focus on inference reliability, latency optimization, and measurable real-world impact.
Education
George Mason University
Master's in computer science, Machine Learning
GPA: 3.87
SRM University AP, India
Bachelor of Technology in Computer Science and Engineering, Machine learning
GPA: 3.6
Experience
-
AI Engineer
BridgeNow AI -
AI Software Engineering Intern
Cyware Labs -
AI Engineering Intern
Gen AI Pioneer -
Web Development Intern
Code Tree Software -
Technical Lead
SRM Innovation Cell
AI Engineer @ BridgeNow AI
Feb 2026 – Present- Architected and shipped Bridgette, a production RAG pipeline backed by LangChain orchestration and semantic search over vector embeddings that intelligently matches users to domain experts at scale, owning full system design from intake through match delivery.
- Designed the end-to-end agent architecture including embedding pipelines, retrieval optimization, and API integration layers, ensuring low-latency inference and reliable LLM output across production workflows.
- Iterated rapidly on prompt orchestration strategies and LLM features in an early-stage startup environment, driving full-stack deployment from model integration to scalable backend API delivery.
AI Software Engineering Intern @ Cyware Labs
Jan 2023 – Dec 2023- Shipped a Vue 2 to Vue 3 migration across 20+ components on real-time threat intelligence dashboards used by SOC analysts, delivering a 30% performance boost and measurable latency reduction in ML-driven insight delivery.
- Resolved 150+ integration failures between frontend interfaces and backend AI services, diagnosing data pipeline bottlenecks and ensuring reliable, lag-free delivery of anomaly detection outputs to end users.
- Built Python automation pipelines that cleaned and normalized raw security logs at scale, cutting manual data preparation by 50% and improving upstream data quality for downstream ML model inference.
AI Engineering Intern @ Gen AI Pioneer
Jan 2022 – Dec 2022- Designed and deployed autonomous Python-based agents to orchestrate complex multi-step NLP workflows using Hugging Face transformers, reducing manual processing time by 65% and improving end-to-end pipeline reliability across enterprise data sources.
- Fine-tuned BERT and DistilBERT models using PyTorch on domain-specific datasets, applying Scikit-learn evaluation metrics to benchmark classification accuracy and measure model reliability improvements across iterative training runs.
- Engineered and tested prompt design strategies across multiple LLM endpoints, systematically measuring response accuracy and reducing output inconsistency through structured evaluation, iteration, and controlled prompt versioning.
Web Development Intern @ Code Tree Software
Jun 2021 – Aug 2021- Architected 10+ dynamic UI pages for the Andhra Pradesh State Warehousing Corporation portal using Angular and Bootstrap, achieving 25% faster page load speeds and full mobile responsiveness.
- Enhanced digital experience for government clients, contributing to a 15% increase in user engagement and more efficient access to logistics and inventory data.
- Collaborated on the full SDLC from design to deployment, integrating features that improved backend data access with SQL databases.
Technical Lead @ SRM Innovation Cell
Dec 2020 – Dec 2022- Mentored 10+ student teams on AI/ML implementation and full-stack prototyping, directly facilitating the launch of 4 campus startups and boosting technical engagement by 30%.
- Architected a resource management portal for the incubation center, reducing administrative latency by 40% and streamlining workflow for student ventures.
- Secured 7 industry partnerships providing students with mentorship and access to technical resources.
Skills
Certifications
Microsoft Fabric Analytics Engineer Associate
Microsoft | Jan 2026
Generative AI with LLMs
NVIDIA | Jan 2026
Agentforce Specialist
Salesforce | Dec 2025
OCI 2024 AI Foundations Associate
Oracle | Oct 2024
Generative AI Fundamentals
Databricks | Aug 2024
Prompt Engineering for Everyone
IBM | Aug 2024
Career Essentials in Generative AI
Microsoft & LinkedIn | Jul 2023
Full-Stack Web Development with React
Coursera | Jun 2022
Foundations of UX Design
Coursera | Jun 2021
My Projects
CONTACT ME AT
- +1 571 420 2558
- vasakoushik@gmail.com
- koushik-vasa