Nlp, Deep Learning, Memory, vector search, embeddings, ML AI pipelines, RAG systems, GenAI models, customer-facing applications, CI CD, Agentic AI solutions, enterprise APIs, multi-agent workflows, chunking, retrieval, time series forecasting, model monitoring, LLM inference architectures, Demand Forecasting, data platforms, MLOps pipelines, prompt engineering, planning, tool-calling, Inventory Planning, drift detection, Governance, autonomous agents

Machine Learning, Deep Learning, Microservices, Python, CrewAI, Generative AI, Agentic AI frameworks, Prompt engineering, LLMs, LangGraph, AutoGen, Vector Databases, Model evaluation techniques, RAG architectures

Amazon Web Services (AWS), Large Language Models (LLMs), Machine learning frameworks and libraries, Developing and deploying AI models in production environments, Python Programming Language, Cloud computing concepts and services

Java, BigQuery, Apis, Cloud Storage, Python, GenAI, Prompt engineering, Agent loops, Google Enterprise Agent Platform, Pub Sub, RAG concepts, Embeddings, Agentic AI, Memory fundamentals, GCP Services, SDKs, Tool integration

Hypothesis Testing, Sql, Tensorflow, Pytorch, Decision Trees, Arima, Keras, Python, Statistical Analysis, KubeFlow, exponential smoothing, support vector machines, Great Expectations, Z-Test, probabilistic graph models, T-Test, Regression, MXNet, Evidently AI, CNTK, ARIMAX, Sci-Kit Learn, BentoML

Sql, Python, tree-based models, R, observability monitoring tools, Generative AI tooling, time-series forecasting, classical ML modeling