Cloud platforms (Azure preferred), Large Language Models (LLMs), Machine Learning Algorithms, Tensorflow, Pytorch, Python, Apache Spark, Sql, Databricks, Prompt engineering, GenAI application development, MLflow, Monitoring and drift detection, Agentic AI workflows, MLOps practices, Distributed computing frameworks, Deep learning frameworks, CI/CD for ML, Vector databases, Lakehouse architectures, Model versioning, Multi-LLM orchestration systems, Statistical Modeling, Embedding models, Automated retraining, Semantic search architectures

analog circuits , Pytorch, Python, EDA Tools, Scientific Computing, Spice, reinforcement learning

workflow engines , Python, tool function calling, tracing observability tooling, Logfire, AI systems in production, prompting, Temporal, OpenTelemetry, pydantic-ai, LiteLLM, MCP, agent architectures

Apache Spark, ELT, Tensorflow, Pytorch, Gcp, Azure, Python, AWS, Etl, LangChain, Hugging Face, Pinecone, FAISS, ChromaDB, LlamaIndex

Machine Learning, Tensorflow, Jenkins, Docker, FastAPI, Python, Kubernetes, Pytorch, Uvicorn, Agentic AI, Encoder-decoder architectures, Pre-processing, Entity extraction, Fine tuning, Similarity matching, Text cleaning, Azure platform

Databases, Apis, Microservices, Python, Machine Learning, Predictive Analytics, Computer Vision, AI application architecture, LLMs, cloud platforms, Agentic AI solutions, AI integrations, Generative AI applications, AI ML frameworks, Forecasting, Ontology and Knowledge Representation, embedding, RAG vector databases, AI-powered search, IoT Connected Systems, Knowledge Graphs

Python, vector stores, data pipeline development, retrieval strategies, re-ranking, multi-step agent workflows, embedding models, prompt engineering, RAG architectures