Top RAG Engineers

I have worked with small and large teams to bring software projects from client ideas to fully realized products. I have experienced this as both developer and tester and understand the communication required on all levels of a project to get the desired product done on time. Managing multiple deadlines for separate projects and different teams has taught me the value of teamwork.

With a Master's degree in Data Science from George Washington University, I am currently applying my expertise as an AI Engineer at Travana. My core competencies lie in RAG and large language models, which have significantly improved our platform's user engagement and reduced customer churn. At Travana, our team has designed a Retrieval Augmented Generation (RAG) system that not only surpassed traditional chatbots but also secured crucial investment by demonstrating the platform's capabilities. My approach prioritizes collaboration, employing advanced technologies to enhance user interaction, which aligns with our organization's culture of innovation and commitment to driving growth through cutting-edge solutions.

BACKGROUND SUMMARY: * Proven Machine Learning Engineer with experience in all phases of ML and Data Lifecycle. * AI Engineering Experience in developing Generative AI applications using OpenAI/LLM api’s, Langchain api, Vector databases, Retrieval Augmented Generation (RAG) techniques. * Experience in machine learning Infrastructure, Model Selection, Model building, Performance Evaluation, MLOps. * Designed Agentic AI applications to automate complex decision-making workflows. * Expertise in Python. * Experience with libraries like scikit-learn, Tensorflow, Keras, pytorch, pandas, numpy, matplotlib, OpenCV. * Good Experience in Big Data Technologies, Hadoop, Hive, Spark. * Experience with AWS cloud Services like Redshift, RDS, Snowflake, EC2, EMR. * Building /training models using AWS Sagemaker. * Utilized Different components of Google Cloud Platform like VertexAI, Gemini. * Tracking of ML Experiments using MLflow. * Knowledge in harnessing Llama 2 models via Hugging Face's Transformers pipeline integration. * Completed numerous online Machine learning, Artificial Intelligence and computer vision courses and obtained certifications. * Extremely interested in working with Multimodal data like audio, images, video. * Good Knowledge of Using and Fine-Tuning Vision Language Models. * Worked on projects to utilize and fine-tune vision models such as YOLO, PaliGemma, Stable Diffusion, and LLaVA. * Both Startup and Fortune 1 Company Experiences with ability to achieve success despite ambiguous requirements and environments. * Expertise includes Data Architecture, Design, Data Analysis, Data Modeling, Data Cleansing, Transformation, Integration, Data import, Data export, Automation, Distributed Systems. TOOLS AND TECHNOLOGIES: DL/ML/CV/AI Libraries: OpenAI api, Langchain, Sklearn, Tensorflow, Keras, pytorch, pandas, numpy, matplotlib, OpenCV,Vertex AI, Gemini, Ultralytics, Roboflow, ADK ML Ops/Infra : AWS , AWS Sagemaker, MLflow, Docker, GCP Languages : Python, Unix Shell Scripting Databases : PineCone, Snowflake, Redshift, Netezza, Teradata, Oracle, postgres, SQL BigData : Hadoop, Hive, Spark ETL Pipelines: Python , DBT, Airflow, Informatica , Talend, BI Tools: Business Objects, Tableau, Thoughtspot, Sisense, Mode Git: https://github.com/venkatram-dev https://github.com/AIBotTeachesAI Youtube: https://www.youtube.com/@AIBotTeachesAI

Hello there , With more than 2 years of hands-on experience in web development, I've been involved in designing, developing, and deploying applications across various technologies and programming languages. I'm looking forward to embracing a challenging role as a Software Engineer where I can apply my broad development experience and technical expertise. I have a passion for crafting seamless, user-centric software applications. Alongside my strong problem-solving skills and ability to thrive in collaborative team environments, I am committed to continuous growth and refinement of my coding skills as a software engineer. Let's connect and explore opportunities to create impactful solutions together!

Hey! I'm Suryansh Gupta, a dedicated and innovative AI/ML developer based in New Delhi, India. Currently, I'm in my final year at Guru Gobind Singh Indraprastha University, specializing in Artificial Intelligence and Machine Learning. Feel free to connect! I'm always open to discussing AI/ML, new technologies, and potential collaborations.

I lead a team building AI-powered retrieval systems in the legal space, with 12+ years at Skadden LLP. I work with open-source LLMs via Hugging Face and PyTorch, alongside hosted LLM APIs such as OpenAI and Anthropic. On the technical side, I focus on agentic retrieval using hybrid search that combines BM25 with vector similarity and rerankers over multi-modal, late-interaction embeddings. I design and implement the full stack, from GPU and API provisioning and cloud LLM environments through search engine architecture to frontend interfaces that make sense to lawyers and business users.

U.S.-based AI Research Scientist with 6+ years of experience in developing small and large language models (SLMs/LLMs), retrieval-augmented generation (RAG) systems, and machine translation. Experienced in reinforcement learning (RL) for model optimization, post-training, evaluation, and deployment of AI systems for global applications. Blog: https://judelee19.github.io/ Google Scholar: https://scholar.google.com/citations?user=Pz8yVqYAAAAJ&hl=en * Authorized to work in the U.S. (Green Card Holder)

I am pursuing a Bachelor of Science in Computer Science and Cognitive Science at Rutgers University-New Brunswick.