Skip to content
Ujwal2910Public

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

1 watching

Forks

Latest commit

 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 

Repository files navigation

Ujwal2910


Ujwal| Twitter

Linkedin

Greetings to all 👋, I'm Ujwal Tewari.


I have been working in Reinforcement learning, control optimization-based techniques and multi-agent systems. In addition to this, I work in the real world deployment of AI-based models for automated control decision processes using both RL and evolutionary strategies in cases where human intervention would otherwise be difficult.

Currently, I serve as a Senior Research Scientist-2 at Games24x7, where I have led multiple initiatives in conversational AI, reinforcement learning, and applied generative AI. My expertise spans:

  • Conversational AI: Multilingual chatbots with language detection/translation, intent classification, and optimized static routing to reduce LLM overhead.
  • Evaluation & Safety: Real-time LLM evaluation pipelines measuring hallucination, relevancy, and completeness; architect of GameGuard, a model-agnostic safety system achieving 99% jailbreak reduction.
  • Reinforcement Learning: Multi-agent RL for traffic intersection management and HVAC optimization using LSTM + RL; goal-oriented dialog systems.
  • Personalization & Recommenders: State-wise CPM/FDA models delivering +5.94% LTP and saving ₹70 lakh/month by eliminating third-party enrichment; localized multimodal recommender systems.

I have also been working as an AI Ambassador at Intel Corporation, a classroom mentor for the Deep Reinforcement Learning nanodegree at Udacity and a tech blogger at Medium in Analytics Vidhya.

Have worked in ML and Research as Senior Applied Scientists for more than 6+ years with good track record of ML papers in reputed conferences

Alongside industry deployments, I have authored application-oriented publications (NeurIPS Deep-RL Workshop 2019, ITSC 2020, submissions to CODS-2025 & EMNLP-2026 ARR) with expertise in model development to deployment lifecycle

My Interests are:

Machine Learning, Reinforcement Learning, Knowledge Graphs, Natural Language Processing and Computer Vision

Here is a bit about my interests and how to get in touch:

  • 💬 I am learning about Model deployment and integration cycles.
  • 🌱 I’m currently working on Generative AI and Multilingua chatbots, Customer service automations, AD recommendation and campaign optimisation, Multi-agent Reinforcement Learning, Dialog systems and Optimization based problems.
  • 💬 Ask me about GenAI, Chatbots, RL, NLP, Deep Neural Networks, GAN, Probabilistic Models and let's Collaborate to knock new ideas to code.
  • 📫 How to reach me: ujwalkaka@gmail.com

Ujwal Tewari Github Stats


About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors