Pivots Hiring
F
78

Founding AI Engineer (Agentic AI)

5y relevant experience

Qualified

Executive Summary

The candidate is a strong senior software engineer with approximately 8 years of experience, most recently working on AI-powered agentic developer tools at Lovable — a directly relevant role involving LLM evaluation, agent workflows, cloud deployment, and external tool integrations. Their background spans Spotify, Zalando, and healthcare companies, demonstrating both technical depth and adaptability across industries. They explicitly claims 0-1 startup experience and an ownership mentality, making them a credible candidate for a founding engineer role. The primary uncertainties are their familiarity with the specific modern agentic frameworks named in the job description (LangGraph, CrewAI, LlamaIndex, LangFuse), the absence of classical ML/data science skills (NumPy, SciPy), and the lack of a public code portfolio. Subject to interview validation on the framework gaps, they represents a strong FIT candidate for this role.

Top Strengths

  • Direct recent experience building AI agent systems, LLM evaluation pipelines, and agentic workflows at Lovable — highly relevant to AlpacaRelay's core product needs
  • Strong full-stack and cloud infrastructure depth across AWS, GCP, Kubernetes, Docker, and PostgreSQL — matches the founding engineer's full-lifecycle ownership requirement
  • Proven track record at well-known companies (Spotify, Zalando, Lovable) demonstrating reliability, senior-level execution, and adaptability across industries
  • Explicitly experienced in 0-1 and 1-10 startup stages with stated ownership mentality and cross-functional collaboration skills
  • Multimodal and tool integration experience (REST APIs, OAuth, webhooks, external productivity tools) aligns well with the real-world integrations required by this role

Key Concerns

  • !Explicit gaps in the specific named agentic frameworks (LangGraph, LangSmith, LangFuse, CrewAI, LlamaIndex) — these are core to the job's technical stack and need to be probed in interviews
  • !No open-source contributions, GitHub profile, or code samples provided — limits technical depth verification and is a listed preference for this founding role

Culture Fit

80%

Growth Potential

High

Salary Estimate

$90,000 – $120,000 USD (aligns with senior range; Poland-based but role is B2B/remote, likely international rate negotiation)

Assessment Reasoning

The candidate meets the minimum requirements comfortably: 8 years of professional experience, proven AI product shipping (Lovable), strong Python and cloud infrastructure skills, LLM/RAG/agent/vector DB experience, and startup readiness. They meets approximately 75-80% of the required skills by substance if not always by name. Their recent Lovable role is essentially a direct analogue to what AlpacaRelay needs. The gaps in named frameworks (LangGraph, LangFuse, LlamaIndex) are real but likely bridgeable given their LangChain depth and AI engineering maturity. The absence of NumPy/SciPy signals a possible gap in classical ML fundamentals, but this is a preferred rather than hard requirement. Overall, they clears the FIT threshold and should advance to a technical interview with focused probing on the framework-specific gaps.

Interview Focus Areas

Hands-on experience with LangGraph, LangSmith, LangFuse, and LlamaIndex — ask specifically whether they have used these or only LangChain; assess ramp-up timelineDepth of ML fundamentals — probe NumPy/SciPy usage, understanding of embeddings, retrieval architectures, and model evaluation beyond prompt engineeringFounding engineer mindset — explore their comfort with ambiguity, technical decision-making in early-stage contexts, and ability to move from prototype to production alone or with minimal supportAgentic AI architecture design — ask them to walk through how they would architect a multi-step AI agent system for a content generation use case

Experience Overview

8y total · 5y relevant

The candidate is a seasoned senior software engineer with ~8 years of experience and a clearly relevant recent role at Lovable, where they built core AI agent workflows, LLM evaluation systems, and cloud deployment infrastructure. Their skill set covers most of the key technical domains required — Python, LLMs, RAG, vector databases, cloud infra, and tool integrations. The primary gap is the absence of explicit references to the named agentic frameworks (LangGraph, LangSmith, LangFuse, CrewAI, LlamaIndex) and classical ML/data science tools like NumPy/SciPy, though their LangChain experience suggests they can likely ramp quickly.

Matching Skills

PythonLangChainRAGLLM EvaluationVector DatabasesAI AgentsMCPPostgreSQLDockerKubernetesAWSGCPCI/CDFastAPIOpenAI/LLM APIsSemantic SearchPineconeGitHub Actions / CI/CDCustom Tooling

Skills to Verify

LangGraph (explicit)LangSmith (explicit)LangFuse (explicit)CrewAI (explicit)LlamaIndex (explicit)NumPy / SciPy (not mentioned)ML fundamentals / data processing (not explicitly stated)Kubernetes (listed in DevOps but no depth shown in AI context)
Candidate information is anonymized. Personal details are hidden for fair evaluation.