Founding AI Engineer (Agentic AI)

4y relevant experience

Under Review

Executive Summary

The candidate is a Solutions Architect and AI Product Engineer based in Krakow, Poland, with approximately 4 years of relevant AI/ML experience primarily through a consultancy role at Delakin Technical Resources Ltd. They demonstrate meaningful alignment with core requirements — particularly LangGraph, RAG, multi-agent systems, and AWS infrastructure — and shows practical applied experience through real AI project examples. However, the role demands a Founding Engineer capable of senior-level technical leadership, and the candidate presents several gaps: missing key tooling (LangSmith, LangFuse, CrewAI, LlamaIndex, Docker/Kubernetes), no verifiable code quality, minimal public technical presence, and no evidence of startup or high-velocity product experience. They are a borderline candidate who warrants a technical interview to validate depth before making a hiring decision, with particular focus on live coding assessment and architecture discussions to confirm whether their consulting experience translates to the senior founding engineer bar this role requires.

Top Strengths

✓Hands-on applied experience building multi-agent AI systems with LangGraph, RAG, and LLM APIs in a consulting context
✓AWS-native architecture skills with real deployment experience (Lambda, DynamoDB, CloudFormation, Lex)
✓Broad ownership mindset covering architecture, CI/CD, IaC, monitoring, compliance, and client-facing work
✓Experience with real-world AI product use cases (financial data agents, content analyzers, candidate screening tools)
✓AI governance and compliance awareness (GxP, HIPAA, PCI, GDPR) which is increasingly critical for production AI

Key Concerns

!No code samples or accessible GitHub contributions to validate engineering quality for a senior founding engineer role
!Material gaps in the required technical stack (LangSmith, LangFuse, CrewAI, LlamaIndex, NumPy/SciPy, Docker, Kubernetes) and no evidence of multimodal AI experience

Culture Fit

60%

Growth Potential

Moderate

Salary Estimate

$70,000 - $95,000

Assessment Reasoning

The candidate is assessed as BORDERLINE (score: 58) rather than FIT or NOT_FIT for the following reasons: On the positive side, they meets approximately 55-60% of required skills, demonstrates real applied experience with LangGraph, RAG, multi-agent systems, OpenAI/Anthropic APIs, and AWS infrastructure, and shows an ownership-oriented background spanning architecture to deployment and compliance. Their project examples (trading data agents, business insights analyzer, AI-powered LinkedIn scraper) align with the agentic AI focus of the role. On the negative side, they are missing critical required tools (LangSmith, LangFuse, CrewAI, LlamaIndex, Docker, Kubernetes, NumPy/SciPy), has no verifiable code samples or accessible GitHub activity, no multimodal AI experience, and no clear startup experience — all of which are important for a Founding AI Engineer at an early-stage product company. The role is explicitly senior and founding-level, requiring someone who can independently architect, ship, and lead — and without evidence of code quality or high-velocity product delivery, the risk of misalignment is meaningful. A structured technical interview with a live coding component and deep architecture discussion is strongly recommended before advancing.

Interview Focus Areas

Deep technical walkthrough of specific LangGraph multi-agent systems built — architecture, design decisions, and production challengesLive coding or take-home assessment to validate Python and AI engineering proficiencyDiscussion of experience with AI evaluation frameworks, observability tooling, and how production AI systems were monitoredExploration of startup vs. consultancy experience and ability to operate with founding-level autonomy and speedAssessment of familiarity with missing stack components (LangSmith, LangFuse, Docker/Kubernetes) and speed of ramp-up

Code Review

FairMid Level

No code example was provided and the GitHub profile was not accessible for review. The candidate references a GitHub account (nansdte2016) in the resume but submitted no code samples. For a senior founding engineer role at an AI startup, this is a notable omission that prevents meaningful assessment of actual engineering quality, style, or depth.

+GitHub account referenced in resume suggests some coding activity exists
+Project descriptions indicate practical implementation of complex AI pipelines

-No code example was submitted with the application despite the role requiring strong engineering skills
-GitHub profile was not directly accessible or reviewed, leaving code quality entirely unverifiable
-For a Founding AI Engineer role requiring production-grade systems, absence of code samples is a significant gap

Experience Overview

9y total · 4y relevant

The candidate presents a reasonably aligned background as a Solutions Architect and AI Product Engineer with hands-on LangGraph, RAG, and LLM integration experience since 2021. Their practical AI project examples (trading data agents, business insights analyzer, LinkedIn scraper) suggest real applied experience with agentic architectures. However, significant gaps exist in the modern AI tooling stack (LangSmith, LangFuse, CrewAI, LlamaIndex, NumPy/SciPy), and the lack of verifiable code samples or public technical presence makes it difficult to confirm depth of expertise.

Matching Skills

PythonLangGraphOpenAI APIsAnthropic APIsVector Databases (Pinecone)Retrieval-Augmented Generation (RAG)MCP Servers and Tool IntegrationsAWS (Lambda, DynamoDB, CloudFormation)PostgreSQL (implied via DB administration background)CI/CDPrompt Engineering

Skills to Verify

NumPySciPyLangSmithLangFuseCrewAILlamaIndexKubernetesGCPGitHub Actions or Similar CI/CD Tools (explicitly)Docker (not mentioned)AI observability/evaluation frameworks (explicitly)Multimodal AI systems (text, vision, speech)

Candidate information is anonymized. Personal details are hidden for fair evaluation.