Machine Learning Operations, Data preprocessing and feature engineering techniques, Cloud-based AI services

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

AWS EKS, FastAPI, Kubernetes, Python, Celery, Sqlalchemy, Airflow, Claude API, confidence calibration techniques, Pydantic, LLM output validation frameworks, embedding models, Weaviate, pgvector, Pinecone, semantic search, RAG context

triton , Pytorch, Kubernetes, Python, Docker, Qdrant, vLLM, LlamaIndex, Airflow, Weaviate, pgvector, LangChain, TGI, CrewAI, Pinecone, LangGraph, GPTQ, MLOps tools, Kubeflow, MLflow, quantization techniques, Scikit-learn, AWQ, Hugging Face ecosystem, AutoGen, GGUF, Weights Biases, FAISS

data engineering , Ml, FastAPI, Kubernetes, Python, AWS EKS, Nlp, Celery, Sqlalchemy, confidence calibration techniques, Airflow, Claude API, vector database, Ai, Pydantic, LLM output validation frameworks, embedding models, Weaviate, pgvector, semantic search, data ingestion pipelines, Pinecone, LLM evaluation frameworks, prompt engineering

Apis, Microservices, system integration, MLops, Microsoft Azure, AWS, cloud-native solution development, continuous integration for AI models, AWS Developer CLI, Agentic AI solutions, GitHub Copilot, AI-assisted coding tools, vibe coding environments

amazon sqs , snowflake , Databricks, Sql, Rabbitmq, New Relic, Golang, Grafana, Postgres, Numpy, AWS, Restful Services, Cassandra, Tensorflow, Python, Nosql, GenAI, ScikitLearn, NLP libraries, Apache Kafka MSK, Agentic AI, MLlib