Founding AI Engineer (Agentic AI)

Executive Summary

The candidate is a highly experienced Senior AI/ML Engineer with 11 years of production-grade engineering across ML, NLP, LLM, and agentic AI systems. Their most recent role at Astronomer is a strong alignment signal — they built RAG pipelines, LangGraph-powered tool-calling workflows, LLM evaluation frameworks, and OpenTelemetry observability systems in a cloud-native environment using Python, AWS, and PostgreSQL. Their experience closely mirrors the core technical requirements of this role. The primary open questions are their familiarity with the specific frameworks explicitly named (LangFuse, LangSmith, CrewAI, LlamaIndex, Anthropic, MCP Servers) and their exposure to multimodal AI systems critical to AlpacaRelay's content product. These are interview-stage verification points, not disqualifiers. With their breadth of experience, mentorship record, and technical depth, the candidate presents a strong founding engineer candidate worth advancing to a technical screen.

Assessment Reasoning

The candidate is rated FIT based on meeting the core minimum requirements and the majority of preferred qualifications for this role. They have 11+ years of experience well above the 2+ year minimum, with the last 3+ years deeply focused on production LLM engineering, RAG, agentic workflows, LangGraph, tool calling, LLM evaluation, and cloud deployment — all central to this role. Their work at Astronomer maps directly to AlpacaRelay's technical stack and responsibilities. Key gaps include the absence of some explicitly listed tools (LangFuse, LangSmith, CrewAI, LlamaIndex, Anthropic APIs, MCP Servers) and no demonstrated multimodal experience. However, these gaps are evaluable in a technical interview and may reflect resume brevity rather than true skill deficiencies. Their certifications, delivery track record with quantified impact, and leadership experience make them a strong founding engineer candidate. The lack of public GitHub or open-source presence is a minor negative for a role that prizes this, but does not disqualify them. Overall, the candidate clears the FIT threshold with confidence.

Interview Focus Areas

The candidate is a seasoned Senior AI/ML Engineer with 11 years of experience and a strong production track record in RAG pipelines, LLM-powered workflows, agentic architectures, and MLOps across cloud environments. Their work at Astronomer is particularly relevant, directly covering LangGraph, tool-calling services, RAG with Amazon Bedrock, LLM evaluation, and OpenTelemetry-based observability. While some specific tools in the job description (LangFuse, CrewAI, LlamaIndex, Anthropic APIs, MCP Servers) are not explicitly named, their experience suggests strong transferable capability across equivalent ecosystems.