Founding AI Engineer (Agentic AI)

1.5y relevant experience

Under Review

Executive Summary

The candidate is an ambitious, early-career AI/Python developer based in Poland who has demonstrated impressive initiative for someone at their stage — building and shipping real AI products within startup environments using OpenAI APIs, LangChain, RAG, and multi-agent workflows. However, at approximately 1.5 years of professional experience, they falls meaningfully short of the senior-level profile this founding role demands, particularly around agentic AI frameworks (LangGraph, CrewAI), cloud infrastructure, MLOps, and large-scale system design. The complete absence of a GitHub portfolio and any public technical presence makes it difficult to objectively assess engineering quality. They represents a high-upside, high-risk candidate — potentially excellent for a mid-level or growth role, but potentially underprepared to serve as a founding technical leader who will mentor others and own critical architectural decisions from day one. If the team is willing to invest in their development and the role can flex toward a 'founding AI developer' rather than a senior technical leader, they could be worth interviewing.

Top Strengths

✓Genuine startup mindset — has built and shipped real AI products with full ownership in fast-moving environments
✓Practical AI integration experience with OpenAI APIs, LangChain, RAG pipelines, and multi-agent workflows
✓Full-stack capability spanning backend (FastAPI), frontend (Next.js), databases (PostgreSQL, Supabase), and deployment (Docker)
✓Quick learner and self-starter who independently tackled complex AI problems without a senior engineering team
✓Clear motivation and alignment with the role's expectations around ownership, iteration, and building from scratch

Key Concerns

!Insufficient experience level (~1.5 years) for a founding senior engineer role that requires autonomous architectural leadership and mentoring other engineers
!Critical tooling gaps (LangGraph, LangSmith, LangFuse, CrewAI, LlamaIndex, Kubernetes, AWS/GCP, MCP Servers) and no verifiable code portfolio to assess engineering quality

Culture Fit

65%

Growth Potential

High

Salary Estimate

$40,000 - $65,000 USD annually (B2B, remote from Poland) — likely below the posted range given experience level and Eastern European market rates

Assessment Reasoning

The candidate is rated BORDERLINE rather than NOT_FIT because they have genuine, relevant experience building AI-powered products in startup environments, which is a hard-to-fake signal. Their projects (multi-agent workflows, RAG pipelines, EdTech platform rebuild) align directionally with the role. However, they do not meet the senior experience threshold the role requires (~1.5 years vs. 2+ minimum, with a senior-level scope), lacks proficiency in the majority of the specific required tools (LangGraph, LangSmith, LangFuse, CrewAI, LlamaIndex, Kubernetes, AWS/GCP, MCP Servers), and has provided no verifiable code artifacts. For a founding AI engineer role where the person must own the entire technical foundation, mentor engineers, and make critical architectural decisions, these gaps are significant. A structured technical interview would be necessary to determine if their practical instincts and learning velocity could compensate for the experience and tooling gaps.

Interview Focus Areas

Deep dive into actual architecture decisions made on the EdTech platform rebuild — what trade-offs were made and whyTechnical assessment of LangGraph and agentic framework knowledge to determine how quickly they could get up to speedCloud infrastructure and deployment experience — probe depth of Docker usage and any exposure to AWS/GCPProblem-solving and system design under ambiguity — how does they approach scaling or reliability challengesMotivation and long-term commitment — understanding their goals given they are currently enrolled in university

Code Review

FairJunior Level

No code examples or GitHub profile were submitted, which is a significant gap for a founding engineering role where code quality and architectural judgment are critical. The projects described in the resume suggest a working knowledge of AI integration patterns, but without code to review, any quality assessment is speculative. For a role with this level of ownership and impact, the absence of a GitHub portfolio is a meaningful red flag.

PythonFastAPILangChainOpenAI SDKFAISSDockerJinja2Next.jsTypeScriptSupabase

+Described implementations suggest understanding of modern AI integration patterns (RAG, streaming, multi-agent)
+Full-stack project delivery indicates ability to work across multiple layers of a tech stack

-No code samples or GitHub profile provided, making it impossible to assess actual code quality, architecture, or engineering discipline
-Cannot evaluate code structure, test coverage, documentation practices, or production-readiness without tangible artifacts

Experience Overview

1.5y total · 1.5y relevant

The candidate is an early-career AI/Python developer with approximately 1.5 years of professional experience, demonstrating genuine initiative and hands-on product delivery across several real projects. They have solid foundational skills in Python, OpenAI APIs, LangChain, and RAG architectures. However, they falls short of the senior-level expectations, lacks proficiency in many required tools (LangGraph, LangSmith, LangFuse, CrewAI, etc.), and has limited exposure to cloud infrastructure, MLOps, and enterprise-scale AI systems.

Matching Skills

PythonOpenAI APIsLangChainPostgreSQLFastAPIRAGNumPyPandasDockerGit/GitHubAnthropic APIs (Claude mentioned)Vector Databases (FAISS)

Skills to Verify

LangGraphLangSmithLangFuseCrewAILlamaIndexSciPyKubernetesAWS/GCPMCP ServersGitHub Actions/CI-CDMultimodal AI systemsMLOps

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