---
title: 'Research Scientist - Model Team at Mirelo AI'
canonical: 'https://feeny.ai/job/research-scientist-model-team-mirelo-ai-berlin-e8rwj2mharj8'
type: 'job'
last_seen: '2026-09-04'
---

# Research Scientist - Model Team at Mirelo AI

- **Company:** Mirelo AI
- **Location:** Berlin, Germany
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2025-12-03
- **Last confirmed live:** 2026-09-04
- **Apply:** https://jobs.ashbyhq.com/mirelo/fb449786-cdb8-4000-8586-3df00c826095

## Job description

Mirelo AI is building the next generation of creative tools by generating realistic sound, speech and music from video.

We develop cutting-edge foundational generative AI models that "unmute" silent video content and create custom, hyper-realistic audio for gaming, video platforms, and creators. Our technology empowers global storytellers to transform their content.

We recently closed a $41 million Seed round co-led by Andreessen Horowitz and Index Ventures with participation from Atlantic, and are rapidly expanding across Product, Engineering, Go-to-Market, and Growth.

## About the Role

At Mirelo, you’ll work at the centre of how we build the next generation of multimodal video-to-audio models. This role is deeply hands-on and research-heavy: with a great H100/200-per-engineer ratio you explore and build new multimodal models and push the boundaries of what’s possible in music, sound, and speech generation. You’ll collaborate closely across research and engineering, run focused ablations, and translate experimental results into clear next steps for the team. From data curation to deployment, you’ll help shape the full lifecycle of the models that power our products and partnerships.

## KEY RESPONSIBILITIES

- Design, implement and train large-scale multimodal generative models for audio generation (diffusion and/or autoregressive models).
- Explore new modeling ideas for audio generation (music, sound, speech) while taking inspiration from the language and image domains.
- Develop and experiment with post-training for new capabilities (fine-grained control, in/out-painting, editing, …)
- Conduct rigorous ablation studies, get actionable insights and communicate results to the team to discuss new research directions.
- Contribute hands-on to all stages of model development including data curation, experimentation, evaluation, and deployment.

## IDEAL CANDIDATE PROFILE

- Hands-on experience in training large-scale generative models in a fast-paced research environment.
- Deep understanding of cutting-edge methods and ML research in at least one of the domains: image, language, video or audio (specific audio experience not necessary, but nice to have).
- Strong proficiency in PyTorch, transformer architectures, and the full ecosystem of modern deep learning.
- Solid understanding of distributed training techniques—FSDP, low precision training, model parallelism
- Strong track-record in working on generative models (publications in top-tier venues, open-source contributions or applied ML projects).

## NICE TO HAVE

- Proficiency with profiling, debugging, and optimizing single and multi-GPU operations using tools like Nsight or stack trace viewers.
- Strong software engineering skills/experience in collaborating on large codebases that go beyond PhD research code.
- Experience with generative models for audio (sound, music or speech) and audio codec design.

WHY JOIN?

- Join at a pivotal moment. We've secured fresh funding and are gaining traction - now is when your contributions can make a real difference to our success.
- True ownership from day one. You'll have genuine autonomy and responsibility. Your ideas and work will directly shape our product and company direction.
- Competitive compensation and equity. We offer strong packages that ensure you share in the success you help create.
- Build for the next generation of creators. Be part of the innovation that will transform how creators work and thrive.

We welcome applications from all individuals, regardless of ethnic origin, gender, disability, religion or belief, age, or sexual orientation and identity.

## About Mirelo AI

## Company Overview
- **One-liner**: Mirelo AI is a frontier AI research lab building audio models that generate custom sound effects and music for videos, synced perfectly to visual content.
- **Entity Type**: Private (Seed-stage)
- **Headquarters**: Tübingen, Germany
- **Founded**: 2023
- **Founders**: Carl Johann Simon-Gabriel (CEO) and Florian Wenzel (Co-Founder & CTO)

## Core Business
- **Primary industry**: Artificial Intelligence (AI Audio Generation), Software Development
- **Target customers**: Video editors, content creators, filmmakers, game developers (Roblox integration), and enterprises via API (B2B & B2C)
- **Mission or purpose**: "Make audio a fun and central part of the creative process, so every frame lands with the emotion, depth, and impact it deserves." — Motto: "Mirelo. Sound on."

## Products & Services
- **Mirelo SFX (Sound Effects)**: Generate realistic Foley, ambiance, and sound effects from video input. Instantly synced to scenes and actions. Available as a plugin for Adobe Premiere Pro, DaVinci Resolve, and Roblox.
- **Mirelo API (SFX 1.6)**: Developer API for integrating AI audio generation into third-party platforms. Supports iterative generation for refined output.
- **Custom Background Music**: Auto-generate ambient and custom background music tailored to video content.
- **Real-Time Audio Editing**: Hear how your edit sounds as you make it — real-time audio that shapes creative decisions from the first cut.

## Market Standing
- **Valuation/Market Cap**: Not publicly available
- **Key Metric**: Total Funding — **$41M** (reports also suggest $44M from conflicting sources)
- **Notable Investors/Partners**: Andreessen Horowitz (a16z), Index Ventures (lead investors)
- **Growth Signals**:
  - Headcount growth of **+109.1% YoY** (now ~15 employees), with 3 active job postings.
  - Website traffic grew **+11680% yearly**; monthly visits ~28,272.
  - Launched SFX 1.6 model in May 2026; integrated with Runware.
  - Strong adoption in Ukraine (66% of traffic), Germany (27%), and growing presence in 6 countries.

## Competitive Advantages
- **Pixel-aware audio generation**: Sound is generated based on scene analysis, not just tags — eliminating the "close enough" compromise of traditional libraries.
- **Real-time iterative editing**: Enables immediate feedback loops, shortening project timelines and accelerating client approvals.
- **Frontier research lab pedigree**: Founded by researchers with deep AI/ML expertise; team includes talent from Meta, Amazon, and Babbel.
- **Multi-platform integration**: Native plugins for industry-standard tools (Premiere Pro, DaVinci Resolve) and platforms like Roblox create low-friction adoption.
- **Full-stack audio**: Combines sound effects, ambiance, and custom music in a single workflow.

## Strategic Focus
- **Model refinement**: Continuously upgrading the core SFX model (v1.6 released May 2026) to improve generation quality and iterative capabilities.
- **API ecosystem expansion**: Targeting enterprise and platform partners to embed audio generation into their workflows (e.g., Runware).
- **Community & creator growth**: Hiring a "Community and Creator Growth Manager" signals a push to build a user community and creator economy around the product.
- **Geographic expansion**: Building out a distributed team across Europe (Germany, Belgium, Poland, UK, Switzerland, India).

## Why Work Here
- **Culture**: Small, research-driven team (15 people) tackling cutting-edge problems at the intersection of AI, audio, and video. Emphasis on "making audio fun."
- **Remote/Hybrid**: Operations across 6 countries (Germany, Belgium, Poland, India, UK, Switzerland) suggest a distributed-friendly environment, though headquarters is in Tübingen, Germany.
- **Team composition**: Heavy on Research (26%) and Technical roles (13%), with alumni from Meta, Amazon, and Babbel — strong engineering and AI pedigree.
- **Growth trajectory**: 109% headcount growth in the last year, active hiring for full-stack engineers and community roles — early-stage opportunity to shape the product and culture.
- **Perks**: Not explicitly listed, but the startup environment with top-tier VC backing (a16z, Index) suggests competitive compensation and equity packages.

## Sources
1. [mirelo.ai](https://mirelo.ai/)
2. [LinkedIn Company Page](https://www.linkedin.com/company/mirelo-ai)
3. [GitHub Organization](https://github.com/mirelo-ai)
4. [Tracxn Profile](https://tracxn.com/d/companies/mireloai/__Ed_uE0ixl33KKO8ognNoJN56KRjBPg44A-6lZBPnNr8)
5. [Ashby Careers Page](https://jobs.ashbyhq.com/mirelo/)

## Other roles at Mirelo AI

- [Community and Creator Growth Manager](https://feeny.ai/job/community-and-creator-growth-manager-mirelo-ai-berlin-qm6z17f65j76) — Berlin, Germany
- [Founder Associate](https://feeny.ai/job/founder-associate-mirelo-ai-09kckfdmd0hx)
- [Principal Product Manager](https://feeny.ai/job/principal-product-manager-mirelo-ai-dgw91b0bp31d)
- [Principal Product Designer](https://feeny.ai/job/principal-product-designer-mirelo-ai-91azndjtvces)
- [Full-Stack Software Engineer](https://feeny.ai/job/full-stack-software-engineer-mirelo-ai-berlin-fv8fz7b2p65w) — Berlin, Germany
- [Research Scientist - Audio Codec](https://feeny.ai/job/research-scientist-audio-codec-mirelo-ai-berlin-wsmzx58n9qjf) — Berlin, Germany
- [Training Infrastructure Engineer](https://feeny.ai/job/training-infrastructure-engineer-mirelo-ai-berlin-2pz6hgas604g) — Berlin, Germany