Posted

Member of Technical Staff - Inference & Hardware Optimization

by Albs

  • Media Production
  • Broadcasting
Freiburg im Breisgau, Germany
Hybrid
Full-time
Professional or Experienced
I’m interested

Free account · stay hidden from your current employer

Your interest is shared with employers only as an anonymized demand signal.

Introduction

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.

Tasks

  • Work across our inference stack end to end: execution engine, memory planning, scheduling, and the low-precision kernels our models actually run on.
  • Work directly with the research team on architecture and quantization decisions, and bring latency, memory and power requirements into the model design.
  • Make real-time multimodal inference fast: streaming, KV cache management, time-to-first-token, and running speech, vision and language components side by side.
  • Squeeze the last few percent out of every target: operator fusion specific to our architecture, cache-aware data layouts and threading. Build on existing runtimes where they serve us, and drop down to SIMD, GPU or NPU kernels when profiling shows that's where the remaining performance is.
  • Bring up new hardware targets, from ARM CPUs and mobile GPUs to vendor NPUs, as we and our customers expand.
  • Build and extend our benchmarking harness: per-layer latency profiling, memory traces, power measurement and accuracy checks across all the hardware we support

Requirements

  • You have several years of hands-on experience in performance engineering for numerical or ML workloads, in industry or research.
  • You write strong systems code in C++, C or Rust.
  • You have optimized ML workloads on constrained hardware at the kernel or runtime level, with hands-on experience in SIMD intrinsics (NEON, AVX), CUDA, or vendor NPU SDKs.
  • You understand low-precision inference and quantization, and how they trade off speed against model accuracy.
  • You are comfortable reading profiling traces and vendor documentation, and working out where the cycles went.
  • Bonus: experience with ML compilers, streaming inference, or speech and vision models on device.

Benefits

  • 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.
Albs

AlbsMelbourne, Australia

Industries
Media Production, Broadcasting
Company size
11-50
Growth
10%