INFUSE is a fully integrated, data-fueled, demand generation engine that offers a host of industry-leading solutions designed to help B2B organizations drive qualified interest. We employ a holistic, omni-channel approach, which empowers us to identify, qualify, and produce actionable engagement.
17 серпня 2026

Senior Fullstack/AI Engineer

віддалено

We are looking for an experienced Senior Fullstack / AI Engineer who will be responsible for end-to-end feature development — from building intelligent AI agents on the backend to visualizing them through intuitive user interfaces.

Why you’ll love this project: We have absolutely zero legacy code. Our entire stack is bleeding-edge (running the latest versions). We don’t just “plug in an OpenAI API key” — we are building a complex distributed system featuring RAG architecture, vector search, event streaming, and big data analytics.

Our Tech Stack

Frontend:

  • Interfaces & Build Tools — Vue 3 / React, TypeScript

Backend:

  • Core Frameworks — Node.js (LTS) + NestJS (core business logic), Python + FastAPI (AI services, orchestration, data processing)

AI & ML:

  • LLM & Orchestration — OpenAI, Anthropic, Google

Data Storage & Messaging:

  • Data Infrastructure — PostgreSQL, ClickHouse, Qdrant, Kafka, Redis, S3 / MinIO

Key Responsibilities

  • Develop end-to-end functionality: from complex interactive interfaces and dashboards to distributed backend services using NestJS and Python.
  • Design and maintain a microservices architecture, ensuring seamless interoperability between Node.js and Python services.
  • Design and optimize data storage schemas across a heterogeneous environment (PostgreSQL, ClickHouse, Qdrant).
  • Implement asynchronous inter-service communication and event streaming via Kafka.
  • Integrate AI components, managing embeddings and semantic search functionality within Qdrant.
  • Optimize application performance, build times, and data processing pipelines.
  • Design and evolve the AI architecture: integrating OpenAI/Anthropic models, managing context windows, and optimizing token consumption (tiktoken).
  • Build and tune RAG (Retrieval-Augmented Generation) pipelines using LangChain and Qdrant vector database.

What We Are Looking For

  • Experience Required: Senior, 4–5+ years in product development, with hands-on experience in LLM integration and data engineering
  • Strong Fullstack Background: Deep knowledge of Node.js, Worker threads, and the NestJS ecosystem (solid understanding of Dependency Injection, Modules, Guards, Interceptors, and Pipes). Proficient in TypeScript (Vue 3, NestJS) and a proven track record of backend development with Python.
  • Hands-on AI/LLM Experience: A solid understanding of prompt engineering, LangChain chains, embeddings, and semantic search. You know exactly how Claude differs from GPT in production environments.
  • Vector DB Expertise: Practical experience with Qdrant (or similar vector databases) — including indexing, similarity search, and vector tuning.
  • Data Infrastructure Literacy: Experience working with distributed systems, message brokers (Kafka), and analytical databases (ClickHouse).
  • Database Mastery: You clearly understand when to query PostgreSQL, when to aggregate data in ClickHouse (OLAP vs. OLTP), and how vector indexes operate in Qdrant.
  • Infrastructure Horizons: Experience with caching (Redis), object storage (S3/MinIO), containerization (Docker/Kubernetes), and the AWS ecosystem.
  • Mindset: Strong analytical skills, a product-driven mindset, the ability to architect fault-tolerant systems, and a dedication to writing clean, maintainable code (SOLID, OOP/FP patterns).

What We Can Offer You:

  • Consistent monthly payment based on invoices (payments are made via bank transfer/ Payoneer or PayPal).
  • Remote working from 14:00 to 23:00 EEST, including a one-hour break.
  • Supportive work/life balance: paid vacation and sick leave.
  • Opportunities for professional and career growth and development.
  • Opportunity to use modern approaches and tools to solve business problems.

Our recruitment process:

  • Interview with HR
  • Technical interview with team leaders
LinkedIn