Soumya Behera
LLM Researcher at Siemens
Chennai, Tamil Nadu, India
Summary
👤
Senior🎓
Top SchoolSoumya Behera is an LLM researcher and Data Science M.Tech student at IIT Madras, currently implementing Graph RAG and knowledge-graph based solutions for building management systems at Siemens. With eight years of hands-on experience bridging machine learning, simulation-driven engineering and embedded systems, Soumya has fine-tuned large language models (Llama3, LLaVa, Meditron) using PEFT, LoRA and QLoRA for domain-specific chatbots. Skilled in Python, C/C++, TensorFlow/PyTorch and classical algorithms, they combine ML expertise with mechanical design and simulation tools (Ansys, Fusion 360, Simulink) to deliver multidisciplinary solutions. Past projects include mobility assistive devices and an award-winning autonomous golf cart team that placed at IGVC and presented at the G20 education forum—evidence of a practical, impact-oriented approach. Outside work, Soumya balances technical depth with a curiosity for literature and film, which influences a user-centered perspective on AI systems.
8 years of coding experience
1 year of employment as a software developer
Indian Institute of Technology MadrasClass 12th, Science (PCM), 97.2%, Class 12th, Science (PCM), 97.2% at BAPS Swaminarayan Vidyamandir
Github Skills (97)
r10
kaggle10
classification10
data-mining10
gradient9
gradient-boosting9
lightgbm9
high-performance9
parallel9
python9
microsoft9
machine-learning9
boosting9
json9
neutralinojs9
Programming languages (13)
Github contributions (5)
Google-Front-End-Weekend-Projects/A-Tribute-To-Stephen-Hawking
Mar 2018 - Mar 2018
Contributions:30 commits, 20 PRs, 27 pushes in 5 days
tributeresponsive-websitecssscholarsgreat
Soumya44/Soumya44.github.io
Jun 2018 - Jul 2019
Contributions:14 commits, 11 pushes, 1 branch in 1 year
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.