Member of Technical Staff - LLM Post-Training

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

Benefits dieser Stelle

Equity

Remote-friendly

Conference support

Zusammenfassung

Albs Labs GmbH in Freiburg, Germany, is seeking staff/senior IC researchers and engineers with deep expertise in post-training LLMs, on-device optimization, and multimodal alignment. You will work on end-to-end post-training, reward modeling, SFT, and RL methods and contribute to high-impact research.

You will publish at top venues, shape our research direction, and collaborate closely with founders in a small, focused team with strong emphasis on rigorous methods and fast iteration.

Qualifikationen

• PhD in a relevant field with additional research or industry experience.
• Post-training LLMs at scale, with deep expertise in SFT, preference optimization, reward modeling or RL, and knowledge of the rest.
• Strong publication record (e.g. NeurIPS, ICML, ICLR) or post-training work shipped in a model.
• Proficient in PyTorch and producing clean, extensible research code.
• Desire to translate research into product impact.

Aufgaben

• Work on post-training of LLMs end to end: data curation, reward models, SFT, preference optimization, and RL methods.
• Post-train models that run on-device: on-policy distillation and alignment under quantization and tight latency.
• Build evaluations to identify gaps in capability, alignment and safety and address them.
• Develop high-throughput post-training and evaluation infra for rapid iteration.
• Collaborate with speech and vision teams to integrate post-training in multimodal models.
• Publish at top venues and help set the research agenda.

Kenntnisse

Post-training LLMs

PyTorch

Research coding

Publication track record

On-device models

Ausbildung

PhD in a relevant field

Tools

TensorRT

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

• Work on post-training of our LLMs end to end: data curation, reward models, SFT, preference optimization, and RL methods such as GRPO.

• Post-train models that run on-device: on-policy distillation from larger teachers, and alignment that holds up under quantization and tight latency budgets.

• Build evaluations that find gaps in capability, alignment and safety, and close them through targeted research.

• Build high-throughput post-training and evaluation infrastructure so the whole research team can iterate quickly.

• Work with the speech and vision teams to bring post-training into our multimodal model without regressing text performance.

• Publish at top venues and help set our research agenda in post-training.

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 post-trained LLMs at scale, with deep expertise in at least one of SFT, preference optimization, reward modeling or RL, and working knowledge of the rest.

• You have a strong publication record (e.g. NeurIPS, ICML, ICLR) or post-training work that shipped in a widely used model.

• You are highly proficient in PyTorch and write clean, well-structured research code that teammates can extend.

• You want your research to make it into the product, with improvements users actually notice.

• Bonus: experience with on-device models, personalization, or multimodal post-training.

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.