Pandas, Numpy, Python, Weights Biases, LangChain, DeepEval, LangFuse, AI system monitoring, RAGAS, AI red-teaming, context architecture for production agents, LangSmith, prompt engineering, OpenAI API, AutoGen, LangGraph, Helicone, LLM evaluation frameworks, adversarial testing, Evals

Ml, Figma, Confluence, Jira, AI workflows, LLMs, Ai, prompt engineering

Rpa, Power Platform, Microsoft 365, Gcp, Scrum, Azure, AWS, LLMs, Ai, cloud AI services, intelligent workflow tools, agile practices, Kanban, ML technologies, lean product methodologies, Design Thinking

Databases, Apis, Workflows, Distributed Systems, System Architecture, AI products, Insurance, Trading, LLMs, Payments, failure modes, Privacy, third-party partners, Banking, Regulatory Requirements, financial rails, Kyc, Remittance, Transaction Monitoring, limits, Licensing, evaluation frameworks for ML or LLM-powered products

Software Engineering, developer tooling, design briefs, Multi-Agent, Agent Loop, evaluation systems, Context Engineering, Reasoning, Prompt Engineering, Planning, Agile development practices, AI agents, MCP Memory, Subagent, LLM-based systems, platform engineering, Tool Use, product prototypes, Source Control, LLM API, building testing frameworks, KV Cache, autonomous workflows