Founding AI Engineer (Agentic AI)
1y relevant experience
Executive Summary
The candidate is an emerging AI engineer from Brazil who punches above their experience weight through ambitious self-directed project work — particularly the OSymandias multi-agent runtime and the Verditta MCP analysis platform, both of which demonstrate genuine understanding of agentic AI architecture relevant to this role. Their professional track record, however, is limited to approximately one year as an IT assistant, and neither a GitHub profile nor code samples were submitted to validate the technical claims. The candidate is geographically in Brazil (B2B remote), which fits the compensation range well, and their growth trajectory and ownership mentality appear strong. The core risk is that this is a founding engineer seat requiring proven production judgment and leadership — and the candidate's verifiable experience base is currently that of a mid-level developer in early formation. A structured technical interview with live coding and deep architecture review is strongly recommended before a hiring decision.
Top Strengths
- ✓Genuine depth in agentic AI architecture demonstrated through OSymandias — a multi-agent runtime with DAG orchestration, vector search, and multi-LLM routing published to PyPI
- ✓Direct hands-on experience with MCP servers, tool calling, and agent orchestration via Verditta — hitting a specific niche requirement of this job description
- ✓Full-stack capability spanning AI backend, distributed systems (Celery/RabbitMQ/Redis), vector databases, and frontend (Next.js) — aligns with founding engineer 'own the whole stack' expectation
- ✓Self-directed learning and shipping velocity: built and published two complex, production-style AI systems independently while still early in their career
- ✓Strong alignment with the specific technology keywords: LangChain, PydanticAI, RAG, vector DBs, Docker, CI/CD, PostgreSQL — suggesting genuine hands-on familiarity
Key Concerns
- !Insufficient verifiable professional experience (approximately 1 year as an IT Assistant) for a senior founding engineer role requiring 2+ years of production AI engineering
- !No submitted GitHub profile or code samples to independently validate the architectural claims made in the resume — verification gap is high risk for a founding hire
Culture Fit
Growth Potential
High
Salary Estimate
$40,000–$65,000 USD (Brazil-based, B2B; well within the $80–120K range if interpreted as blended or US-equivalent rate for remote)
Assessment Reasoning
The candidate is rated BORDERLINE rather than FIT due to a meaningful gap between their resume's ambitious AI engineering narrative and the verifiable professional experience underlying it. They meets approximately 55–60% of the required skills based on resume claims, with strong alignment on agentic AI concepts, MCP, RAG, Python, and distributed systems. However, they falls short on: (1) minimum experience threshold — ~1 year professional vs. 2+ years required, and no prior formal AI engineering role; (2) missing critical skills including LangGraph, LangSmith, LangFuse, Kubernetes, AWS/GCP, and NumPy/SciPy; (3) no submitted code samples or GitHub link to verify technical claims; and (4) a thin LinkedIn profile that doesn't corroborate the resume's depth. On the upside, the OSymandias and Verditta project descriptions — if accurate — reflect architectural thinking that meaningfully exceeds their experience level and shows genuine passion for the problem space. For a founding engineer role specifically, the stakes of a mis-hire are high, but so is the potential upside of an early-career engineer who is already building production-quality agentic systems. A rigorous technical screening round is recommended to determine whether this candidate's real capabilities justify overriding the experience gap.
Interview Focus Areas
Code Review
No code was submitted for direct review, making a definitive quality assessment impossible. Based solely on project architecture descriptions, the candidate demonstrates mid-to-senior conceptual thinking in distributed AI systems design. A GitHub portfolio review or take-home technical assessment would be essential before drawing firm conclusions about actual code quality and engineering craftsmanship.
- +OSymandias project demonstrates sophisticated architectural thinking: DAG orchestration, multi-queue Celery setup, vector search integration, and SSE observability in a single coherent system
- +Publishing to PyPI and designing for framework-agnostic extensibility (LangChain, CrewAI, LlamaIndex via decorator pattern) shows API design maturity beyond junior level
- -No actual code samples were submitted for review — all assessment is inferred from project descriptions, which may overstate complexity or completeness
- -GitHub profile was not provided, preventing verification of code quality, commit history, documentation standards, or actual codebase inspection
Experience Overview
1y total · 1y relevantThe candidate presents a technically ambitious resume anchored primarily in substantial personal projects rather than professional work experience. Their open-source multi-agent runtime (OSymandias) and the MCP analysis platform (Verditta) reveal genuine depth in agentic AI architecture, distributed systems, and LLM integration that significantly exceeds what their single listed job title suggests. However, the gap between their claimed expertise and verifiable professional track record is a meaningful concern for a founding engineer role requiring proven production experience.
Matching Skills
Skills to Verify