I'm Anshuman Kumar, a Senior Consultant specializing in Machine Learning Engineering, Agentic AI systems, and production-ready Generative AI solutions. Areas of Expertise: ML Engineering: End-to-end model lifecycle management using Python, XGBoost, PyTorch, TensorFlow, and Feast. Experience in training, tuning, deployment, and monitoring of ML models in real-world environments. Agentic & Generative AI: Building autonomous LLM-based agents using LangChain, OpenAI APIs, and vector search (PGVector, FAISS). Hands-on with RAG pipelines, tool integrations, and structured output workflows. Semantic Search & Summarization: Developing GPT-powered retrieval systems that blend unstructured content search with context-aware generation. Cloud Deployment: Experience with GCP (Cloud Run, GKE, Firebase), AWS (Lambda, SageMaker), and CI/CD pipelines for AI workflows. Conversational AI (Secondary Focus): Background in Dialogflow, RASA, and Lex with multilingual bot deployments. Tech Stack: Python, FastAPI, Node.js, LangChain, OpenAI, DeepSeek, HuggingFace, PyTorch, TensorFlow, XGBoost, SQL, Firestore, Elasticsearch, Docker, Kubernetes. I focus on scalable, modular AI systems—ranging from classical ML to LLM-centric applications—optimized for reliability, cost, and real-world business impact. Portfolio: anshumankumar.dev LinkedIn: linkedin.com/in/anshumankumarcs Email: anshumankumar.mail@gmail.com