Senior Software Engineer - Data & AI Platform (m/w/d)
At a glance
Senior ML Platform & Ops role at vivenu GmbH. Frankfurt/Düsseldorf · full-time.
Pay not stated ML Platform & Ops salary
aimlroles summary, based on the employer's posting.
What you'll do
- Connect MongoDB transaction data to ClickHouse so reporting can aggregate ticket activity quickly
- Build RAG workflows that turn natural-language questions into reliable SQL and aggregation queries
- Develop Go or TypeScript/Node.js services for live dashboards while protecting transaction performance
- Work with platform and security teams on data schemas, audit trails, and checks for inaccurate results or metric shifts
- Join monthly Frankfurt architecture sessions to shape technical milestones with engineering leaders
What you bring
- At least five years building distributed, high-throughput production services in Go, Python or TypeScript/Node.js
- Hands-on production work with ClickHouse or a comparable low-latency analytics engine
- Practical knowledge of MongoDB and PostgreSQL, plus experience with production RAG systems and evaluation methods
- Understanding of event streaming through Kafka, RabbitMQ or cloud pub/sub
Who this fits
This senior engineering role suits someone comfortable owning production data and AI systems with a pragmatic, validation-focused approach. It includes monthly in-person architecture sessions in Frankfurt.
From the employer
With over 10 million end users and usage quadrupling annually, our infrastructure now handles over 1 billion requests per month — and counting. Our API-first platform solves complex system challenges at scale — delivering performance, flexibility, and reliability for the world’s leading live entertainment brands.
As a Senior Software Engineer - Data & AI Platform (d/f/m) your responsibilities will include:
-
Build Analytical Query Engines: Connect our transactional backends (MongoDB) with modern analytical event stores (ClickHouse) to support sub-second aggregations across millions of ticket transactions.
-
Implement AI Retrieval & Reporting Workflows: Build and deploy Retrieval-Augmented Generation (RAG) pipelines, semantic parsers, and agentic query supervisors that convert natural language prompts into deterministic, accurate SQL and aggregation queries.
-
Maintain Low-Latency Reporting APIs: Write high-performance production services in Go or TypeScript/Node.js that power real-time reporting dashboards for global organizers without degrading transactional processing.
-
Centralize Data Flows & Auditing: Partner with platform and security teams to build clean data schemas, strict audit trails, and automated evaluation suites that catch hallucinated data or metric drifts before they reach clients.
-
Sprint Scoping & Architecture: Collaborate directly in monthly in-person architecture sessions in Frankfurt alongside the VP of Engineering, CTO, and engineering leads to define technical milestones.
Your Responsibilities:
What you will need to succeed in this role:
-
5+ years of hands-on experience building high-throughput, distributed production services using Go, Python, or TypeScript/Node.js.
-
Analytical Warehousing Experience: Direct, hands-on production experience with ClickHouse (or closely related low-latency analytical engines like DuckDB, Snowflake, or Apache Pinot) for high-volume event streams.
-
Database Mastery: Solid practical experience with both document/NoSQL stores (MongoDB) and relational engines (PostgreSQL).
-
Production AI / RAG Engineering: Proven experience deploying production RAG systems, function calling, evaluation frameworks, and supervisor architectures (e.g., LangGraph, LlamaIndex, or custom orchestration layers).
-
Event-Driven Architectures: Strong understanding of distributed message streaming using Kafka, RabbitMQ, or cloud pub/sub mechanisms.
-
Pragmatic Mindset: High autonomy and scrappiness—you choose reliable, deterministic validation layers and battle-tested databases over fragile AI hype.