Member of Technical Staff - Speech Language Models

Albs Labs GmbH; Freiburg im Breisgau; Hybrid; EUR 120.000 - 180.000; Vollzeit

Benefits dieser Stelle

Equity

Flexible work model

Zusammenfassung

Albs Labs GmbH is seeking a Staff / Senior IC to advance state-of-the-art speech language models. You will work across ASR, TTS, and speech-to-speech, driving end-to-end development and real-time capabilities on-device.

This role collaborates with hardware and software teams to push the boundaries of multimodal AI. You will lead research and engineering efforts, with a track record of publications or production impact, and you will thrive in a fast, collaborative environment in Freiburg,

Qualifikationen

• PhD or equivalent with several years of research/industry experience.
• Experience training speech models at scale (ASR/TTS/speech-to-speech).
• Strong understanding of audio representations and LLM integration.

Aufgaben

• Develop and train speech language models end to end (ASR, TTS, speech-to-speech).
• Research audio tokenizers and neural codecs balancing quality, bitrate, latency.
• Design for real-time streaming, turn-taking, and tool calling on-device.
• Build evaluations for accuracy, naturalness, latency, and turn-taking in conversations.
• Collaborate with hardware teams on low-latency on-device inference.
• Publish at top venues and shape research agenda in speech language models.

Kenntnisse

Python

PyTorch

Distributed training

Low-latency systems

Research & publications

Ausbildung

PhD in relevant field

Tools

PyTorch

Jobbeschreibung

About us

Albs is an AI research lab building real-time multimodal intelligence for machines, enabling them to see, hear, reason, and interact. We treat model architecture, inference, and runtime as one system. Our purpose-built models and optimized runtimes unlock the full potential of each device within defined limits for hardware cost, power consumption, and response time. Companies can adapt our technology to their own machines without building the underlying AI from scratch.

We founded Albs at the intersection of LLM architecture research and on-device engineering, and we are currently in stealth, but well funded, with dedicated compute for large-scale training and experimentation. Publishing is a core part of our research culture, and we contribute our work to top venues. We share more details about the company, the team and our backing in the first conversation.

Who we're looking for

This is a Staff / Senior IC role. We are looking for experienced researchers and engineers, typically with a PhD and several years of research or industry experience or an equivalent track record. The exact scope of each role depends on your background: some people go deep on one part of the stack, others shape the technical direction of a whole area. We agree on scope together with you during the interview process. We welcome applications from all qualified candidates, regardless of gender, age, ethnic origin, religion, disability or sexual orientation.

What you'll work on

• Develop and train our speech language models end to end, from ASR and TTS to full speech-to-speech, both adapter-based on top of our LLM and as end-to-end full-duplex models.

• Research and evaluate audio tokenizers and neural codecs that balance quality, bitrate and latency.

• Design for natural interaction: streaming, turn-taking, interruptions and tool calling in real time, robust to noise, distance and multiple speakers.

• Build evaluations for what matters in real conversations: accuracy, naturalness, latency and turn-taking quality.

• Design for the hardware from the start: evaluate architectures for low-latency, on-device inference together with the hardware optimization team.

• Integrate the speech component into our multimodal language model without regressing text performance.

• Publish at top venues and help shape our research agenda in speech language models.

What we're looking for

• You hold a PhD in a relevant field and have several years of research experience after it, in academia or industry, or an equivalent track record.

• You have trained speech models at scale, such as ASR, TTS or speech-to-speech, ideally from scratch.

• You have a deep understanding of audio representations: codecs, discrete and continuous tokens, and how they interact with an LLM backbone.

• You have experience with streaming, low-latency speech systems, such as full-duplex dialogue or voice agents.

• You have a strong publication record (e.g. Interspeech, ICASSP, NeurIPS, ICML, ICLR) or an unambiguous production track record in speech.

• You have deep Python and PyTorch proficiency and experience with distributed training at multi-node scale.

• You move between research and engineering, and want results that hold up on real hardware and in real conversations.

• Bonus: experience with multilingual speech, speech post-training, or audio safety.

How We Work Together

We are a small, focused team of experts. You would join early, work directly with the founders, and help shape how we build. Fast iteration, short lines of communication, and in-person discussion matter a lot to us. Our culture is built around the office in Freiburg, Germany, with a default of three days a week on site. Alternatively, you can work remotely and join us on a regular cadence. We will discuss what works best for you during the interview process.

We hold ourselves to a high standard: the research must be rigorous, the understanding deep, and the product well crafted. Ideas are judged on their merit, not on who proposed them, credit belongs to the team, and no task is beneath anyone. We make ambitious bets and ship early instead of waiting for perfect conditions. Above all, we care about each other, because initiative only works when it comes with respect for the people around you.

What we offer

Expect a competitive base salary plus equity, and dedicated compute for your research and experiments. We give you the time and support to publish and present at top conferences, and flexibility in how you work, whether on site or remote with regular in-person visits. With flat hierarchies and short decision paths, good ideas move from discussion to experiment quickly. And yes, the coffee is excellent, and we regularly get together as a team outside of work. We go through compensation and all other details with you early in the process.