Top LLM Engineers

A Microsoft certified AI developer and Machine Learning Engineer with hands-on experience building Generative AI and Agentic AI systems. I focus on turning unstructured data and complex documents into actionable, searchable intelligence using Retrieval-Augmented Generation (RAG) pipelines. Currently interning at Gisfy Private Limited (Hyderabad), where I architect RAG applications using LangChain, LlamaIndex, and OpenAI APIs, and optimize LLM outputs through structured prompt engineering and agentic workflow design. Recent work includes: Building an end-to-end RAG pipeline (LangChain + Groq Llama-3.3-70B) with Chroma vector search and LangSmith observability for document intelligence A fully local, voice-enabled LLM chatbot for people mental health support ML classification models detecting psychological risk indicators at 95% accuracy Tech I work with: Python, LangChain, LangSmith, ChromaDB, HuggingFace Embeddings, Groq/OpenAI APIs, Scikit-Learn, TensorFlow. I'm actively growing in the GenAI and applied ML space and open to Data Science / AI Engineering roles. Let's connect!

A highly adaptable individual with a strong ability to thrive in diverse environments and a proven track record of personal and professional growth.

I work in tech, focusing on AI, Machine Learning, Generative AI, and Large Language Models. I enjoy using Python to build chatbots and smart AI tools. I'm really interested in how AI can solve real-world problems and make things easier and smarter. Always curious and excited to learn more!

ML Engineer (Deep learning / Generative AI) with 12+ years of experience building AI-driven solutions across computer vision, document intelligence, and generative AI. Currently working at Tata Consultancy Services (TCS) on domain-specific LLM applications and intelligent automation. Previously served as Lead Engineer (Team Lead) at Straive (SPI Global), developing large-scale ML pipelines for STM publishing, OCR, image validation, and content verification. Strong hands-on experience with Python, PyTorch, LLM fine-tuning, RAG, multimodal models, and GPU-accelerated systems. Passionate about building scalable, reliable AI solutions that deliver measurable business impact. Core Skills: Python, PyTorch, TensorFlow, Computer Vision, OCR, LLMs, RAG, Hugging Face, LangChain, OpenCV, Transformers, Multimodal AI, AWS, Docker, Kubernetes, FastAPI, PostgreSQL, Vector Databases (FAISS, Milvus), Git

Staff / Lead Software Engineer specializing in production-grade Agentic AI and Generative AI systems. I design and build LLM-powered applications that operate reliably in real-world, high-stakes environments, with a focus on evaluation, observability, guardrails, and scalable deployment. Experience includes: – Agentic AI workflows (LangGraph, ReAct-style agents) – RAG systems (vector + graph-based, multi-modal) – LLM evaluation and production monitoring – Kubernetes-based deployment and inference optimization Previously worked on large-scale ASIC and DSP systems, bringing a strong systems engineering mindset to modern AI platforms.

A first-principles software engineer specializing in developing highly scalable backend applications, and NLP systems utilizing large language models (LLM).

Experienced AI Engineer / Data Scientist with expertise in designing and deploying Generative AI applications, LLM-integrated systems, scalable data pipelines, and AI-powered analytics solutions. Proficient in RAG pipelines, SQL automation, deduplication engines, and interactive dashboards, with a strong command over Python, FastAPI, Streamlit, Power BI, and modern MLOps tools (Docker, FAISS, ChromaDB).