Laxman Tomar

About

With a Bachelor of Technology in Computer Science and Engineering from Dr. A.P.J. Abdul Kalam Technical University, this professional has a strong educational foundation. Their experience includes roles such as Senior ML Engineer at Jiffy.com, Senior NLP Engineer at Emplay Inc., and Machine Learning Engineer at Albot Technologies, where they led the development of various AI-powered tools and systems. They also contributed to projects at Robofied and Aegisisc Software Solutions Pvt Ltd, showcasing their expertise in speech/voice-based functions, content development, and technical writing. Their work involves integrating generative capabilities of LLMs like GPT-3 & ChatGPT, building conversational search experiences, and developing AI-powered content moderation engines. With a focus on machine learning, natural language processing, and computer vision, they have consistently demonstrated their ability to innovate and deliver impactful solutions.

Experience

• Senior ML Engineer · Jiffy.com08-01-2023

  Digital Assets Management Platform - one stop to search and shop 5M+ digital assets. Designed and architected the Service involving components like Metadata Generation, Indexing and Search. Used LLMs (GPT-4 Vision and Claude Models) for assets metadata generation (design, aesthetics, occasions etc.) and classification (artwork/mockups/illustrations etc.). Used ElasticSearch for Indexing. Later, Hybrid Search (Vector Search (MiniLM) and Keyword Search (BM25)) with Reranking (TinyBERT) are used for search capabilities. Available as Design Library on Jiffy.com. Jiffy Copilot - Built a conversational search assistant to assist you in shopping products you'd love. Powered by chaining multiple calls via LLMs (GPT-4-Turbo and GPT-3.5-Turbo) and Vector Search (using indexed catalog in ElasticSearch), it allows users to search and add multiple products to cart. It gathers requirements from users efficiently, asks follow-up questions and takes care of users' budget and inventory. Available to iOS users of Jiffy.

• Senior NLP Engineer · Emplay Inc.01-01-2022 – 08-01-2023

  Conversational Search Engine: Currently integrating generative capabilities of LLMs like GPT-3 & ChatGPT into products like Search, Generation, Information Retrieval, and multi-purpose Agents for SAP and P&G via LLM Stack including LangChain. Knowledge Search Engine: Architected a scalable microservice-based system to build and search a knowledge index with over 1 million documents for P&G, supporting multiple tenants and controlled hierarchy via configs. Utilized Docker and Kubernetes for orchestration and OpenAPI standard for REST API design. Question-Answer Generation: Built a pipeline for generating high-quality question-answer pairs from indexed text documents, using T5 and Roberta models fine-tuned on the SQUAD dataset. Designed and implemented asynchronous request handling with Celery and RabbitMQ and deployed it as REST APIs using FastAPI in Docker and Kubernetes. Developed a monitoring dashboard and a testing suite for unit and stress testing with Pytest and Locust. Question-Answer Evaluation: Annotated a dataset of low and good-quality QA pairs, and adopted techniques like Weak Supervision and Active Labeling to improve annotation efficiency. Generated features attributing to question presence, grammatical question structure, and text readability. Developed a Random Forest Classifier with ~75% accuracy to filter out low-quality questions, with data and experiment tracking by DVC and MLFlow. Developed an evaluation suite to identify low-confidence samples via CleanLab and key slices via Snorkel/Sliceline. Content Moderation Engine: Developed an AI-powered content moderation engine for Simpplr, utilizing a dataset comprising ~2M comments. Trained a Mini-LM Model to detect racial, religious hate, insulting, and explicit comments with ~91% accuracy. Utilized ONNX Conversion and Dynamic Quantization to optimize the solution for speed and storage space. Served in production with FastAPI and Docker and actively used by 500+ companies.

• Machine Learning Engineer · Albot Technologies09-01-2020 – 01-01-2022

  Led the build of SafeNet: Under the aegis of UNICEF Innovation Fund, an AI-powered extension meant to detect & handle visual, toxic content prevalent over the web in order to safeguard the internet browsing experience of children. Worked on building Cyber Anomaly Detection System: an ML-based tool to automatically detect network anomalies and 14 different types of attacks such as DoS, DDoS, Heartbleed, and others in real-time. Worked on building Homoglyphs Phishing Detection System: an ML-based tool to automatically detect visually similar phishing domains via CNNs and to safeguard user information. Worked on building Email Phishing Detection: an ML-based tool to analyze various properties of raw email files and predict whether incoming emails are phishing emails or not in real-time.

• Machine Learning Engineer · Robofied08-01-2019 – 09-01-2020

  Working on Voicenet-a comprehensive python library for performing speech/voice based functions ranging from Speech to Text, Gender;Age and Emotion detection from Voice and many more! Creating Content in as technical write-ups, blogs, case-studies and mini projects and efficient models by using bleeding-edge state of the art techniques and tools.

• Machine Learning Intern · Robofied06-01-2019 – 07-01-2019

  Worked on Identification of the Gender of the Speaker based on Voice Samples with commendable accuracy in order to provide human alike behavior by Model.

• Content Developer · Aegisisc Software Solutions Pvt Ltd03-01-2020 – 06-01-2020

  Working on creating quality technical write-ups and blogs on the topics ranging from intricacies in traditional Machine Learning to state-of-the-art Models in Computer Vision and Natural Language Processing.

Education

• Dr. A.P.J. Abdul Kalam Technical UniversityBachelor of Technology, Computer Science and Engineering

Similar talent on Pangea

Harshit S.Machine Learning Engineer | AI SpecialistNew York, NYSunil T.Software Engineer | AI Enthusiast | Project ManagementToronto, ONMuhammad I.Full Stack Developer | NLP | Machine Learning | Data Scientist | AI Agent and Automation DeveloperMultan, PakistanSaidi S.AI Engineer (LLMs, RAG Systems, Multimodal AI) — Backend & Scalable Production SystemsTunis, Tunisia