Lead AI / n8n Solutions

Pastoraltech
Занятость Полная занятость
Полная занятость
Адрес Узбекистан, Ташкент
Описание вакансии

We’re looking for a Lead AI / n8n Solutions Engineer to take ownership of designing and delivering cutting-edge agent-based AI workflows. This person will both build and lead, driving innovation across our AI stack — from vector database integration to low-code orchestration using n8n.

This is a highly autonomous, impact-driven role ideal for someone with a builder mindset and proven ability to lead small, focused engineering teams. You'll be instrumental in shaping the foundation of multiple AI-powered products launching this year.

Core Responsibilities

Technical Delivery:

  • n8n Architecture:
    Build and maintain low-code pipelines that:

    • Ingest LLM prompts

    • Query vector stores (Qdrant, pgvector, etc.)

    • Run agent loops

    • Trigger downstream actions (e.g., Stripe payments, badge issuance)

  • Full-Stack AI Integration:
    Select and connect best-fit LLMs (GPT-4o, Claude, local) and embedding models for live use cases.

  • RAG System Ownership:
    Ensure smooth performance and accuracy through prompt engineering, embedding strategies, and query optimization.

  • Guard-Rail Logic:
    Implement semantic validation and vector-based checks to prevent hallucinated or broken output.

  • DevOps (Lite):
    Monitor token usage, latency, and cost spikes. Own alerting and response protocols for the AI layer.

Leadership:

  • Tech Guidance:
    Mentor AI and backend engineers working on agent logic, pipelines, and API layers.

  • Architecture Ownership:
    Review architecture decisions across the AI stack and ensure long-term maintainability.

  • Cross-Functional Collaboration:
    Work closely with product and design to translate goals into scalable, production-ready systems.

  • R&D Direction:
    Stay ahead of trends in LLM ops, vector search, and agent frameworks to continuously improve product capabilities.

Stack Snapshot

LayerTech

Low-code / Orchestrationn8n

LLM GatewayLangChain → GPT-4o / Claude / local

Vector DBQdrant / pgvector / Pinecone

API LayerFastAPI on AWS Fargate

DevOpsToken + latency alerting, cost monitoring

DownstreamStripe, badge issue, CMS systems

We’re hiring fast — if you're ready to lead, build, and innovate, we’d love to hear from you.

Требования
Опыт Более 6 лет
Условия работы
График работы Полный день
Добавлено 5 дней назад
Для связи с работодателем или просмотра контактов нажмите на кнопку