Tusher Chakraborty

About Tusher Chakraborty

I am a Researcher at Microsoft Copilot Tuning, where I work on aligning the LLMs underlying Microsoft Copilot with enterprise customer preferences. My work sits at the intersection of reinforcement learning, reward modeling, and LLM post-training, with a focus on making alignment both technically rigorous and practically scalable. A central challenge in this space is that comprehensive human annotation is expensive and hard to scale. My research addresses this from multiple angles: designing hybrid human-AI feedback pipelines that concentrate human effort where it matters most, building reward signals that capture reasoning quality at the token level without succumbing to reward hacking, and developing rubric learning systems that continuously discover new quality dimensions rather than saturating on a fixed set of criteria. More recently, I have extended these alignment techniques to long-horizon agentic workflows, where Copilot must handle multi-step reasoning and tool use across live enterprise environments.

Experience

1. Principal Research Manager

   Microsoft

   Sep 2025 — Present · Redmond, WA, US

Education

• Bangladesh University of Engineering and Technology

  Bachelor of Science (B.Sc.), Computer Science and Engineering

  2015

• Bangladesh University of Engineering and Technology

  Master's degree, Computer Science

  2015 — 2017

Skills

• Embedded Software Programming
• Mysql
• Microcontrollers
• Matlab
• Arm
• Iot
• Sensor-Enabled Embedded Systems
• C++
• Python
• C
• Gprs
• Assembly Language
• Xilinx
• Electronics Hardware Design
• Embedded Systems
• Interfacing
• Nfc
• Arm Cortex-M
• Ieee 802.11
• Embedded Networking
• Laser Cutting
• Fpga
• Quantum Computing
• Verilog
• Gsm
• Java
• Arduino
• Pcb Design
• Real-Time Operating Systems (Rtos)
• Php
• Atmel Avr
• Hardware and Software Interfacing
• C#
• 802.15.4
• Azure Iot Hub