Docker, Pi, FastAPI, Kubernetes, Python, LangChain, Claude Code Skills, multi-agent architectures, Hermes Agent, cloud platforms, Claude Code, LangGraph, RAG, evaluation frameworks, MCP, agent orchestration

Docker, Openshift, Databricks, FastAPI, Kubernetes, Python, LangChain, token usage tracking, Azure OpenAI Service, LangGraph, AWS SageMaker, latency benchmarking, LLM-based applications, RAG architectures

snowflake , Pyspark, Kafka, API design, Grafana, Microservices, Python, AWS, Java, Redis, Gcp, Memcached, Spark, Data Governance, Dynatrace, Databricks, Splunk, Azure, Apache Iceberg, Airflow, data lake architectures, Temporal, agentic architectures, LLM-based applications, AI ML systems, NoSQL databases, vector stores, LLM orchestration frameworks

Aws Lambda, Apis, Graphql, Sql, React, Git, Typescript, ECS, Iam, Python, Api Gateway, AWS, n8n, Amazon EKS, OpenAI Codex, GitHub Copilot, Next.js, GenAI applications, RAG solutions, Amazon Bedrock

MLops, Neo4j, AI ML, MongoDB, eval-driven development, embedding, AI observability, RAG architecture, document pipelines, LLMOps, Cloud cost optimisation, re-ranking, DORA metrics, LangChain, AWS Bedrock, data-driven model evaluation, responsible AI controls, LangGraph, production-grade reliability, chunking, engineering standards, vector databases, SageMaker, managed inference infrastructure, similarity thresholds, prompt tracing, output evaluation, hallucination detection, prompt discipline, AWS Neptune