Senior AI Engineer

About ChatRevenue.ai

ChatRevenue.ai was founded by Ratmir Timashev (founder of Veeam) and Vlad Voskresensky (founder of Revenue Grid).

We are building an agentic sales automation for post-CRM era. The AI-native product combines structured and unstructured data, LLM workflows, and agentic automation to help sales people to focus properly, work more efficiently and automate repetitive sales processes.

The product is already being tested by early customers. We are growing the core engineering team and looking for people who want to work on real product systems with direct impact on architecture, quality, and speed of delivery.

About the role

We are looking for a Senior Generative AI Engineer with 5+ years of commercial Python experience and hands-on experience building production GenAI / RAG systems.

This is a hands-on engineering role focused on:

Python backend

LLMs and RAG

AI Copilot / assistant workflows

We are looking for someone who can take a problem, propose a practical solution, and move it to production.

What you will do

Design, build, deploy, and maintain production GenAI / RAG pipelines

Integrate LLMs and agentic assistants into product workflows

Improve latency, reliability, scalability, and cost-efficiency of AI systems

Evaluate and implement new GenAI, multi-agent, and orchestration frameworks

Contribute to architecture and technical decisions across the platform

What we are looking for

5+ years of commercial Python experience

Strong backend experience with FastAPI, APIs, webhooks, Docker, Kubernetes, Git, and CI/CD

Commercial experience with LLMs in production

Strong hands-on experience with RAG, retrieval workflows, embeddings, and vector search

Experience with LangChain, LangGraph, LangSmith, or similar frameworks

Good knowledge of SQL, Pandas, ETL, data cleaning, and ingestion pipelines

English: B2 or higher

High ownership, independence, and product mindset

Nice to have

Multi-agent LLM systems

Knowledge graphs, graph databases, or graph-based retrieval

Kafka, Azure Event Hub, or other event-driven systems

Azure cloud infrastructure

Production ML / NLP systems

Evaluation, tracing, observability, and optimization of AI pipelines

Graph algorithms or tools like NetworkX

What we offer

Remote-first setup

Flexible schedule aligned with European time zones

A core engineering role in an AI-native product

Direct influence on technical decisions and architecture

Real ownership and visible product impact

If you have strong Python backend fundamentals and real production GenAI / RAG experience, we’d love to talk.