Siddhant Bharti

Senior Machine Learning Engineer at Together AI, working on agentic AI systems and large language models. AI researcher with 5+ years of experience and an MS in Computer Science from the University of Maryland, College Park, with published research on LLM reliability at NeurIPS and EMNLP.

Publications

Tool Preferences in Agentic LLMs are Unreliable
Kazem Faghih, Wenxiao Wang, Yize Cheng, Siddhant Bharti, Gaurang Sriramanan, Sriram Balasubramanian, Parsa Hosseini, Soheil Feizi
EMNLP 2025 · arXiv · PDF
LLM-Check: Investigating Detection of Hallucinations in Large Language Models
Gaurang Sriramanan, Siddhant Bharti, Vinu Sankar Sadasivan, Shoumik Saha, Priyatham Kattakinda, Soheil Feizi
NeurIPS 2024 · PDF · Code · Poster
An Inference Algorithm for Multi-label MRF-MAP Problems with Clique Size 100
Ishant Shanu, Siddhant Bharti, Chetan Arora, S. N. Maheshwari
ECCV 2020 · PDF

Projects & Open Source

CoderForge-Preview
Co-author of the largest open test-verified coding-agent dataset: 258K trajectories across 51K tasks. Fine-tuning Qwen3-32B on it reaches 59.4% on SWE-Bench Verified — #1 among open-data models at ≤32B parameters.
Together AI · Dataset on Hugging Face
RELAI Sets New State-of-the-Art for LLM Hallucination Detection
Wenxiao Wang, Siddhant Bharti, Priyatham Kattakinda, Soheil Feizi
RELAI Blog, Nov 2024 · Archived post

Experience

Senior Machine Learning Engineer
Together AI · May 2025 – Present
Agentic AI systems and large language models; co-author of the CoderForge-Preview coding-agent dataset.
Graduate Research Assistant
University of Maryland, College Park · 2023 – 2025
Research on LLM reliability: hallucination detection (NeurIPS 2024) and tool-use robustness in agentic LLMs (EMNLP 2025).
Senior Software Engineer
Instabase · Jan 2022 – Jul 2023
Led design and development of AIHub, Instabase's first B2C SaaS platform for intelligent document processing.

Education

M.S. in Computer Science
University of Maryland, College Park
2023 – 2025
B.Tech
Netaji Subhas Institute of Technology (NSIT), Delhi
2014 – 2018

Research Interests

Agentic AI Systems, LLM Safety and Hallucination Detection, Scaling Deep Learning, Computer Vision, Convex Optimization