Headline

Lead Applied Scientist at 8bit.ai | Multi-Agent Systems, Text-to-SQL, Enterprise Search, LLM Infrastructure

About

8bit.ai focuses on scaling and optimizing LLM inferencing pipelines for open-source models on GPU clusters, contributing to cutting-edge AI advancements. Prior to this, SuperAGI enabled the development of SuperCoder 2.0, an autonomous software development system, and spearheaded fine-tuning techniques like Instruct FT and DPO for instruct models. The National Institute of Technology Meghalaya laid the foundation for core competencies in AI and computer science, complemented by practical experience in multi-agent systems, model fine-tuning, and generative AI. Dedicated to advancing scalable AI solutions, they aim to bridge research and real-world applications.

Location

Bengaluru

AI stack

antigravity

claudecode

Work experience

Lead Applied Scientist AI/ML at 8bit.ai, Oct 2024 - Present · 1 yr 11 mos, Bengaluru, Karnataka, India, 1) Leading the design and development of production-grade AI systems at 8bit.ai across agentic platforms, enterprise search, Text-to-SQL, and multimodal applications. 2) Architecting Neutrino, a multi-agent AI platform for workflow automation, data analysis, and tool-augmented execution, with support for human-in-the-loop workflows, multi-LLM orchestration, and production-ready backend infrastructure. 3) Built custom Agent Platform to offer agentic Text-to-SQL systems for multi-schema environments, enterprise search and RAG pipelines, and data intelligence solutions spanning retrieval, metadata enrichment, schema understanding, and knowledge-graph augmentation. 4) Working on scalable LLM deployment and optimization through inference benchmarking, pruning, quantization. 5) Fine tuning of custom SLMs and Preference alignment using DPO. 6)Training small reasoning models using GRPO

Applied Scientist AI/ML at SuperAGI, May 2024 - Oct 2024 · 6 mos, Bengaluru, Karnataka, India · Hybrid, Building SuperCoder 2.0, an Open Source autonomous Software Development System

AI Product Engineer at SuperAGI, Nov 2023 - May 2024 · 7 mos, Bengaluru, Karnataka, India · Hybrid, 2) Research - Part of the core research team at SuperAGI. - working on model Finetuning techniques - Instruct FT, DPO, etc. - Dataset creation for chat and instruct models. - Agentic Frameworks facilitating multi agent collaborative chat applications. 1) Development of SAM-v1, small agentic model based on Mistral 7B. - Development of Explanation traces to fine tune mistral 7b - Used Yi-34B-Chat, Falcon - series, and Mixtral to generate Rationales - SAM achieved performance comparable to GPT 3.5 and outperformed Orca on GSM 8k. - The aim was to fine tune Mistral 7b with explanation/reasoning traces of better models to achieve better problem solving capability. Blog : https://superagi.com/introducing-sam-small-agentic-model/ HuggingFace : https://huggingface.co/SuperAGI/SAM

Associate Consultant at Oracle, Aug 2022 - Oct 2023 · 1 yr 3 mos, Bengaluru, Karnataka, India, 2) Working in AI/ML to develop POCs and implementing client requirements for automation using Python. Working with frameworks like TensorFlow and PyTorch. Developing Semantic search system for closed domain Question answering using LLMs. Using different open source tools to quickly develop NLP and Document Understanding application. Along with working on OCI AI Services to deliver to client needs. 1) Worked with client to analyze the functional requirements and migrate SOA integrations to OIC Gen2. Analyzed SOA composites for ERP and CRM based systems.

Research Intern at NVIDIA, May 2021 - Apr 2022 · 1 yr, Bangalore Urban, Karnataka, India, Worked on Deep Learning algorithms and used frameworks like Nvidia Nemo, Nvidia Tao, etc.

Education

Master of Technology - MTech, Computer Science, National Institute of Technology Meghalaya

Bachelor of Technology - BTech, Information Technology, Vellore Institute of Technology