Top RAG Engineers

Currently contributing as a Technical Intern at Ellucian, leveraging skills in knowledge graph databases, graph-RAG, vector databases, and embeddings. With a strong academic foundation in computer science with data analytics from KPR College of Arts Science and Research, the work integrates theoretical knowledge with practical applications. Actively enhancing expertise through certifications, including deep learning for NLP and advanced AI engineering. Passionate about applying emerging technologies to solve complex challenges, with a focus on data-driven innovation and continuous learning.

AI Engineer with 1.2 years of prior experience in Angular-based frontend development, now focused on building LLM-powered applications and intelligent automation systems. With a strong foundation in Angular, JavaScript, HTML, CSS, REST APIs, and SQL, I bring full-stack awareness to AI system design — understanding both user-facing interfaces and backend intelligence layers. Currently working on client-deployed AI solutions, designing multi-LLM workflows, structured data extraction systems, and voice-enabled chatbot architectures. Experienced in building Retrieval-Augmented Generation (RAG) systems using embeddings and vector databases (ChromaDB), integrating conversational memory, and implementing dynamic routing using Pydantic models. Contributed to developing intelligent chatbots capable of extracting structured information through LLM-generated schemas, backend execution layers, and response consolidation pipelines. Worked on automation workflows using n8n, requirement extraction bots, Jira ticket automation, and voice-based clarification systems using OpenAI APIs. Strong hands-on experience with Python, FastAPI, Streamlit, SQLite, and scalable backend architecture. Currently exploring graph-based AI systems using Neo4j. Passionate about designing practical, scalable AI systems that solve real-world business problems through clean architecture and intelligent automation.

Software Engineer with 2.5 years of experience specializing in Generative AI, LLMs, and NLP. Currently working on AI-driven solutions including AI agents, RAG-based systems, and automation workflows using OpenAI and Claude APIs. Experienced in building scalable pipelines for text processing, prompt engineering, and real-world AI applications. Skilled in Python, LangChain, embeddings, vector databases, and system design. Passionate about building intelligent systems and solving real-world problems using AI.

I build AI systems that actually work in the real world, not just in notebooks. My focus is on agentic AI and LLM-powered applications, designing multi-agent workflows, RAG pipelines, and intelligent decision systems that operate at scale in production environments. Currently, I'm shipping AI that automates financial underwriting for merchants, processing millions of decisions with sub-60s latency on Azure + Databricks. Before that, I spent time at AI4Bharat (IIT Madras) contributing to multilingual NLP platforms used across 20+ Indic languages, working alongside researchers, linguists, and engineers to build tools that bring AI closer to India's linguistic diversity. What I care about most is the intersection of reliability and intelligence, building AI that doesn't just perform well in demos but holds up under real-world constraints: regulated environments, audit trails, edge cases, and all. My stack revolves around Python, LangGraph, LangChain, RAG, MCP, PyTorch, and cloud infrastructure (Azure, Databricks), but I pick tools based on the problem, not the other way around. A few things I'm proud of: Global Top-50, Google Solution Challenge 2022 (4,000+ teams) APAC Finalist, Generation Google Scholarship 2022 (top 0.001% of applicants) 9.29 CGPA | 7th Rank university-wide, MAIT Delhi I'm always up for conversations about agentic systems, LLM architecture, or just what's breaking in production this week.

I’m a Software Engineer with 3 years of professional experience in machine learning, computer vision, end-to-end pipeline development. Over the past few years, I’ve worked on projects that span the entire ML lifecycle — from training and fine-tuning deep learning models, to deploying them in production with frameworks like NVIDIA DeepStream, Openvino, and Triton Inference Server, to building supporting data pipelines with python, fastapi, SQL and NOSQL databases.What excites me most is taking a research idea or prototype model and turning it into a reliable, scalable system that delivers real-world impact. I’ve built real-time object detection solutions for applications like license plate recognition and safety monitoring, optimized inference pipelines to cut latency and streamline deployment.Recently, my focus has expanded into Generative AI and Large Language Models (LLMs). I’m exploring techniques like Retrieval-Augmented Generation (RAG), prompt engineering, LLM fine-tuning, Agent building to apply foundation models to enterprise and custom use cases. My background in traditional ML and computer vision gives me a strong technical base, while my hands-on software engineering experience ensures I think beyond models — into usability, scalability, and maintainability.Looking ahead, I aim to specialize in AI/ML engineering roles that combine deep technical work with practical deployment at scale. Whether it’s optimizing inference pipelines, designing end-to-end GenAI systems, or building AI-powered applications, I’m driven by the challenge of making cutting-edge technology accessible, reliable, and impactful.

I'm a Cognitive Engineer with hands-on experience in Python-based backend development, automation frameworks, and Generative AI solutions. Proficient in building RESTful and gRPC APIs using FastAPI, along with end-to-end and functional test automation using Robot Framework and Pytest. Experienced in developing RAG, Agentic RAG, and multi-agent systems using LangChain, CrewAI, and GPT-4. Skilled in embeddings, vector databases, Model Context Protocol (MCP), and semantic search using FAISS. Strong exposure to Docker, GitLab CI/CD, Linux, and Agile development practices, with a solid understanding of networking and distributed systems.

With over 8 years of experience in machine learning, deep learning, and natural language processing, I specialize in creating robust, scalable, and efficient solutions leveraging large language models (LLMs). My expertise spans from theoretical foundations to practical implementations, consistently pushing the boundaries of AI advancements. I excel in Python and have hands-on experience in statistical analysis, enabling me to deliver innovative and impactful results in diverse applications. Passionate about harnessing the power of AI to solve real-world problems, I am committed to continuous learning and contributing to the future of technology.

AI/ML Engineer with expertise in developing and deploying AI solutions to production environment. Key skills and expertise: Specialization in AI agents, Agentic AI, in-context learning and RAG, Graph RAG (Knowledge Graphs) and advanced prompting techniques including Chain-of-Thought (CoT), Tree-of-Thought (ToT), ReAct and Meta Prompting. Proficiency in working with LLMs (GPT, Llama, deepseek, phi models) and Fine-tuning LLMs(gpt-4o-mini). Expertise in embeddings, vector databases(Qdrant, Faiss, CromaDB, Pinecone), Graph Database(neo4j) semantic search, and hybrid search techniques Technical proficiency: Programming: Python, SQL Cloud: Azure (AI Services, Document Intelligence, Blob Storage, Cosmos DB, Key Vault) Frameworks and tools: LangChain, Llama Index, CrewAI, LangGraph, n8n, RAGAS, Opik, DeepEval, Arize AI, OpenEvals, Flask APIs and Streamlit