Latency and cost thinking, Eval discipline, RAG fundamentals, Strong backend engineering, LLM pipeline engineering, Responsible AI and data privacy awareness, Prompt lifecycle management

data pipeline, API design, Tensorflow, Pytorch, Docker, Python, AWS, Gcp, Azure, Kubernetes, CI CD for AI, Pinecone, backend systems, Mistral, Distributed microservices, model monitoring, LangChain, LLaMA, LLMs, Anthropic, FAISS, xVector DBs, RAG, drift detection, Milvus, OpenAI, Weaviate

Node.js, Jinja2, Sql, Typescript, FastAPI, Python, LangChain, Hugging Face, Pinecone, Transformers, Milvus, LlamaIndex

Rest Apis, Cursor, Kubernetes, Python, Docker, Generative AI, fine-tuning techniques, Prompt Engineering, AI agents, LLM-based applications, embeddings, Windsurf, RAG, microservices architecture, cloud-native application development, GitHub Copilot

data engineering , Machine Learning, Pyspark, Tensorflow, Numpy, Pytorch, Docker, Python, AWS, Java, Natural Language Processing, Deep Learning, Azure ML, Pandas, MLops, Kubernetes, Mathematics, R, GCP AI Platform, Spark MLlib, Generative AI, Scikit-learn, Statistics, SageMaker, Julia

Tensorflow, Numpy, Pytorch, Gcp, Pandas, Docker, Azure, Python, Kubernetes, AWS, LangChain, Hugging Face, MLflow, OpenAI APIs, Transformers

Gcp, Cloud deployment, FastAPI, Azure, AWS, CrewAI, LangGraph, RAG pipelines, vector database, prompt engineering

Java, Node.js, Azure ML, Gcp, Azure, Python, AWS, LangChain, LLMs, Hugging Face Transformers, MLflow, embedding models, vector databases, Kubeflow, Vertex AI, Transformers, Diffusion models, RAG pipelines