Github, Windows Server, Ssh, Dns, Http, Firewalls, routing, Jenkins, Git, Linux, Wmi, Cloud Infrastructure, SNMP, WinRM, Vector databases, REST API design, Advanced Python development, Infrastructure Engineering

System Design, Flask, Software Engineering, FastAPI, Python, LangChain, CrewAI, Agentic AI frameworks, GenAI LLMs, observability of AI systems, LangGraph, AutoGen, embedding, MCP, cloud-native architectures, evaluation monitoring, RAG Vector Databases, semantic search

Memory Management, Python, LangChain, AWS Bedrock, Agentic AI frameworks, token spend optimization, multi-agent orchestration, RAGAS, prompt injection prevention, context window management, model-agnostic experience, LangGraph, automated AI RAG evaluation pipelines, autonomous agentic workflows, AI agents, Azure AI

Pytorch, Linux, Docker, Python Programming, PEFT, Hugging Face Transformers, open-source LLMs, model routing, prompt engineering, GPU-based inference and optimization, Evaluation, structured extraction, LoRA, NVIDIA GPU infrastructure, reranking, RAG, Generative AI LLMs

Tensorflow, Nlp, Pytorch, Docker, Python, AWS, Gcp, MLops, Azure, Kubernetes, GloVe, Hugging Face, MLflow, Pinecone, LLM architecture, Word2Vec, RAG pipelines, ChromaDB, fine-tuning techniques, LangChain, LLM training methodologies, LoRA, QLoRA, sentence transformers

MLops, Docker, Kubernetes, Python, LLM orchestration frameworks, LLMOps, vector databases, RAG pipelines, prompt engineering

Tensorflow, Azure ML, Pytorch, Python, embeddings, LLMs, scikit-learn, prompt engineering, vector stores, SageMaker, GCP Vertex AI, RAG, Cloud ML infrastructure