Founding AI Engineer (Agentic AI)
4y relevant experience
EU engineers, ready to place with your US clients
Pre-screened on AI. Remote B2B contracts. View 5 full profiles free — AI score, skills report, interview questions included.
Executive Summary
The candidate is a strong candidate for the Founding AI Engineer role, bringing 5 years of software engineering experience with approximately 1.5 years deeply focused on production GenAI and agentic AI systems. Their work at FOLIUM AI directly mirrors the responsibilities outlined — building multi-tenant AI SaaS platforms, designing RAG pipelines, and implementing LLM evaluation frameworks at scale. Their technical breadth across Python, LangGraph, CrewAI, vector databases, and cloud infrastructure aligns well with the founding engineer scope. The primary concerns are the absence of public code artifacts, a LinkedIn URL discrepancy, and gaps in a few specific required tools (LangSmith, LangFuse, LlamaIndex, MCP). A structured technical interview with a practical agentic AI challenge would be the decisive factor in confirming a full fit for this role.
Top Strengths
- ✓Direct production experience building multi-tenant GenAI SaaS platforms with agentic workflows
- ✓Solid command of agentic AI frameworks including LangGraph and CrewAI in enterprise settings
- ✓Full-stack depth from AI/ML pipelines to cloud deployment (AWS, GCP, Kubernetes) — essential for a founding engineer
- ✓LLM evaluation and observability mindset (Ragas, LLM-as-a-Judge) critical for production AI quality
- ✓5 years of progressive engineering experience with leadership and mentorship track record
Key Concerns
- !LinkedIn URL mismatch and lack of GitHub/public code artifacts reduce verifiability of claimed skills
- !Gaps in specific required tooling (LangSmith, LangFuse, LlamaIndex, MCP servers, Anthropic/OpenAI APIs explicitly) could slow onboarding in a fast-moving startup environment
Culture Fit
Growth Potential
High
Salary Estimate
$80,000 - $110,000
Assessment Reasoning
The candidate is assessed as FIT with moderate-to-high confidence. They meets approximately 65-70% of the explicitly listed required skills, with particularly strong alignment on the most critical competencies: Python engineering, LangGraph, CrewAI, RAG pipelines, vector databases, LLM evaluation, cloud infrastructure, and full-stack ownership. Their current role at FOLIUM AI is essentially a direct analog to what AlpacaRelay is hiring for. The missing skills (LangSmith, LangFuse, LlamaIndex, MCP servers) are learnable tools within a closely related ecosystem they clearly operates in, rather than fundamental gaps. The score of 74 clears the FIT threshold of 70. Key risks — the LinkedIn mismatch, no code samples, and no GitHub — prevent a higher confidence score and warrant thorough technical validation before extending an offer.
Interview Focus Areas
Code Review
No code example or GitHub profile was provided by the candidate, making it impossible to directly evaluate code quality, style, or engineering depth. The resume suggests strong engineering practices through mention of Clean Architecture and production deployments, but these claims remain unverified. A technical interview or take-home assessment would be essential to validate actual coding ability.
- +Resume describes production-grade system design suggesting solid engineering discipline
- +Experience with Clean Architecture and microservices implies structured, maintainable code practices
- -No code sample, GitHub profile, or open-source contributions were provided — direct code quality cannot be assessed
- -Cannot verify hands-on depth of claimed LLM/agent framework experience without code artifacts
Experience Overview
5y total · 4y relevantThe candidate is a Senior Full Stack AI Engineer with 5 years of experience, including approximately 1.5 years in a directly relevant GenAI/agentic AI role at FOLIUM AI. Their technical profile strongly overlaps with the job's core requirements in Python, LangGraph, CrewAI, RAG, vector databases, and cloud infrastructure. However, some specific tooling gaps (LangSmith, LangFuse, LlamaIndex, MCP servers) and the absence of code samples or GitHub presence slightly limit confidence in a full fit assessment.
Matching Skills
Skills to Verify