Principal AI System Engineer

As a Principal AI Systems Engineer, your role involves architecting, building, and owning AI systems that automate expert-intensive technical workflows end-to-end. You will be responsible for solving real business problems with AI, ensuring full implementation and adoption of solutions, and measuring their effectiveness. Your responsibilities include: - Architecting end-to-end AI automation systems, including workflow decomposition, component communication, human checkpoints, and failure behavior. - Designing and building internal CLI frameworks, reusable libraries, and agent scaffolding. - Authoring and maintaining agent instruction files (SKILL.md, CLAUDE.md, system prompts) and MCP server definitions. - Configuring Claude Code and Codex CLI environments, including MCP wiring, tool permissions, slash commands, and engineering standards. - Evaluating and documenting architectural trade-offs across reliability, latency, cost, and maintainability. In addition, you will be responsible for: - Building production-grade AI pipelines in Python, including orchestration, structured prompting, context assembly, schema validation, and retry strategies. - Integrating AI systems with external tooling such as version control, build pipelines, SDKs, and compliance. - Designing, versioning, and maintaining system prompts and agent instructions as engineering artifacts. - Engineering context windows with precision balancing accuracy, token cost, and latency through compression and selective retrieval. - Implementing full audit trails for inputs, tools called, outputs, and human review triggers. - Enforcing versioning of all agent instructions and system prompts with controlled rollout. For this role, you are required to have: - A proven track record of building production AI automation systems from scratch end-to-end. - Hands-on expertise with Claude Code, Codex CLI, Cursor, or equivalent tools. - Experience designing and deploying MCP servers and custom tools. - Proficiency in building internal CLI frameworks, agent scaffolding, and reusable libraries. - Experience in prompt and context engineering, system prompts, token budget management, and prompt versioning. - Knowledge of LLM orchestration frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen, or equivalent. - Experience in building AI evaluation frameworks and production Python engineering. - Cloud platform experience with AWS, Azure, or GCP for deploying and monitoring AI workloads with containerization. Bonus points will be given for experience integrating AI systems with external APIs, tool definition, permission management, and failure handling. As a Principal AI Systems Engineer, your role involves architecting, building, and owning AI systems that automate expert-intensive technical workflows end-to-end. You will be responsible for solving real business problems with AI, ensuring full implementation and adoption of solutions, and measuring their effectiveness. Your responsibilities include: - Architecting end-to-end AI automation systems, including workflow decomposition, component communication, human checkpoints, and failure behavior. - Designing and building internal CLI frameworks, reusable libraries, and agent scaffolding. - Authoring and maintaining agent instruction files (SKILL.md, CLAUDE.md, system prompts) and MCP server definitions. - Configuring Claude Code and Codex CLI environments, including MCP wiring, tool permissions, slash commands, and engineering standards. - Evaluating and documenting architectural trade-offs across reliability, latency, cost, and maintainability. In addition, you will be responsible for: - Building production-grade AI pipelines in Python, including orchestration, structured prompting, context assembly, schema validation, and retry strategies. - Integrating AI systems with external tooling such as version control, build pipelines, SDKs, and compliance. - Designing, versioning, and maintaining system prompts and agent instructions as engineering artifacts. - Engineering context windows with precision balancing accuracy, token cost, and latency through compression and selective retrieval. - Implementing full audit trails for inputs, tools called, outputs, and human review triggers. - Enforcing versioning of all agent instructions and system prompts with controlled rollout. For this role, you are required to have: - A proven track record of building production AI automation systems from scratch end-to-end. - Hands-on expertise with Claude Code, Codex CLI, Cursor, or equivalent tools. - Experience designing and deploying MCP servers and custom tools. - Proficiency in building internal CLI frameworks, agent scaffolding, and reusable libraries. - Experience in prompt and context engineering, system prompts, token budget management, and prompt versioning. - Knowledge of LLM orchestration frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen, or equivalent. - Experience in building AI evaluation framework