Pytest, Phoenix, Typescript, Jest, Python, allure, DeepEval, Playwright, RAGAS, Arize, LangSmith, Cypress, Promptfoo

Test Architect, Automation, Agentic AI

Apis, Microservices, Rest Apis, Python, LLM and agent evaluation frameworks, model governance, RAG architecture, LLMs, reusable AI components, metadata filtering, embedding models, vector databases, agent memory design, tool-calling capabilities, agent development frameworks, retrieval strategies, backend services, Document Processing, observability and tracing, guardrails for AI agents, multi-agent orchestration patterns, automation scripts

Java, API design, Docker, Kubernetes, Python, LangChain, CrewAI, AWS Bedrock, pgvector, Qdrant, Go, Pinecone, OpenSearch, AutoGen, LangGraph, LLM orchestration frameworks, Weaviate, LlamaIndex, Claude SDK

Graphql, Elk, Sql, React, Typescript, Gcp, Javascript, Docker, Rest Apis, Python, Kubernetes, MLops, AWS ECS, GKE, CI CD, LangSmith, OpenAI Agents SDK, MCP, OpenAI tracing, STT, TTS, RAG, VAD latency optimization, Voice realtime agents, Temporal workflows

Cloudformation, CDK, Lambda, Kms, Terraform, Iam, Api Gateway, AWS, Data Protection, GenAI, Step Functions, multi-account landing zones, SageMaker, VPC design, Amazon Bedrock, AWS Well-Architected Framework, agentic AI solutions, Knowledge Bases, AgentCore, Agents, serverless services, Guardrails, RAG pipelines

Data Privacy, Containers, Python, Access Control, AWS Bedrock, Lang Chain, Lang Graph, Auditability, Lang Smith, Graph technologies, AI Eval tools, Semantic Kernel, Infrastructure as code, Model risk, Llama Index, CI CD pipelines, Serverless deployment, Responsible AI, AI governance

Servicenow, Automated Testing, Nlp, Javascript, Python, Rest Apis, embeddings, vector search, event-driven patterns, Privacy, AI CrewAI, LangGraph, Evaluation, responsible AI, Security, LLM-powered applications, chatbots, model evaluation techniques, observability, tracing, RAG patterns, Monitoring, AI assistants, voicebot