🇩🇪 Berlin, Germany · 2w ago
Systems Software Engineer (Rust, ML Inference)
ai-coustics
LinkedInmidEnglish-friendly€75k–95k
ai-coustics is building the reliability layer for Voice AI, the system that closes the gap between raw audio input and reliable machine understanding in production. By combining state-of-the-art speech and audio research with real-time, production-grade SDKs, we test, observe, and enable Voice AI systems to work in any environment. Our software is used by fast-growing Voice AI companies across Europe and the United States whose products require reliable performance at scale: call center agents, voice agents, telephony apps, and enterprise voice assistants. We believe voice will become the main interface for technology and ai-coustics is building the foundational infrastructure to make audio input reliable, measurable, and easy to deploy.We are backed by leading early-stage investors including Connect Ventures, Partech, Inovia Capital, as well as angel investors from HuggingFace, DeepMind and Amazon with deep expertise in AI and developer infrastructure. These partners share our vision and are helping us build a world-class team operating with high levels of responsibility and velocity. We look for people who take ownership, think systemically, and want to solve challenging real-world problems in close collaboration with our customers. If you're motivated by developing technology that is used in practice, shaping an emerging category and setting a new standard for how voice AI works in the real world, you'll feel at home at ai-coustics.Role Overviewai-coustics is seeking a Systems Software Engineer to join our Systems team, working at the core of our real-time Audio AI SDK and inference infrastructure. In this role, you will help maintain, optimize, and expand the SDK that powers ai-coustics' speech enhancement and Voice AI products across a wide range of platforms, runtimes, and languages.You will work primarily on our Rust-based inference and systems codebase, which underpins the Airten real-time inference engine, DSP modules, telemetry, model execution pipeline, and public SDKs used by developers worldwide. Your work will directly impact model performance, runtime efficiency, reliability, developer experience, and our ability to deploy neural audio models in latency-critical production environments.This role sits at the intersection of systems programming, ML inference, real-time audio, and developer infrastructure. You do not need to be an ML researcher, but you should be excited about making neural networks run fast, safely, and predictably in real-world applications.Ideal starting date: August/SeptemberTasksML Inference Engine & Runtime DevelopmentDesign, implement, and optimize systems-level components of the ai-coustics SDK and inference runtimeImprove the performance, memory usage, and stability of the Airten real-time inference engineWork on model execution, tensor operations, scheduling, streaming inference, and runtime abstractionsSupport deployment of neural audio models across CPU, WASM, and other constrained runtime environmentsExplore and integrate ideas from modern inference engines and ML runtimes such as Burn, ONNX Runtime, tract, TensorRT, or similar systemsHelp bridge the gap between research models and production-ready, low-latency inferenceAudio, DSP & Real-Time ML SystemsDevelop and maintain DSP modules and supporting audio-processing infrastructureOptimize streaming workloads under strict latency, jitter, and memory constraintsBuild tooling to validate numerical correctness, real-time behavior, and model quality across platformsCollaborate with ML researchers to make models easier to export, test, benchmark, and deployContribute to model conversion and deployment workflows, including formats such as ONNX, internal model formats, or Rust-native representationsLanguage Bindings & Platform SupportMaintain and expand our C API and public C library generated from our internal Rust codebaseImprove and support SDK wrappers and bindings for C++, Python, and Rust via the public C APIMaintain WASM and Node.js SDKs built directly from the internal Rust sourceEnsure consistent behavior, performance, and API guarantees across Linux, macOS, Windows, WASM, and embedded-adjacent environmentsTesting, Reliability & ToolingDesign, implement, and extend our testing pipeline, including unit tests, integration tests, numerical tests, and performance benchmarksBuild tooling to validate real-time constraints, memory usage, model outputs, and cross-language consistencyImprove CI workflows to ensure safe and fast iteration on a closed-source core with public-facing SDKsCreate benchmarks and profiling workflows that help us understand runtime bottlenecks and performance regressionsImprove observability and diagnostics for SDK integrations in customer environmentsDocumentation & Developer ExperienceWrite and maintain technical documentation for SDK APIs, runtime internals, model deployment, and integration guidesCollaborate with product and developer-facing teams to improve onboarding and usabilitySupport internal teams and external developers by diagnosing SDK and inference issues and proposing robust fixesContribute to API design with a focus on ergonomics, safety, portability, and long-term maintainabilityRequirementsTechnical SkillsStrong experience in systems programming, ideally with RustSolid understanding of C/C++ interoperability, ABIs, and FFI designExperience building or maintaining SDKs, libraries, inference runtimes, or developer-facing systemsFamiliarity with real-time systems, performance optimization, memory management, and profilingExperience writing tests and benchmarks for low-level or performance-critical codeComfortable working across multiple platforms such as Linux, macOS, Windows, and WASMAbility to reason about API design, unsafe boundaries, ownership, error handling, and long-term maintainabilityML Inference & Audio SystemsFamiliarity with ML inference runtimes or deploying neural networks in productionExperience with model formats or inference engines such as ONNX, Burn, tract, TensorRT, TFLite, Core ML, or similar systemsUnderstanding of how neural networks are represented, executed, optimized, and benchmarkedExposure to real-time audio constraints such as latency, jitter, buffering, streaming workloads, and deterministic processingInterest in making ML models portable, efficient, and reliable outside of Python research environmentsMindset & CollaborationStrong ownership mentality and attention to detailComfortable working in a closed-source core with open SDK surfacesAbility to reason about trade-offs between performance, safety, portability, and developer experienceClear written communication skills for documentation and technical design discussionsEnjoys working in a fast-moving startup environment with real-world production impactExcited about building infrastructure that helps Voice AI systems work reliably in messy, real-world audio conditionsBenefitsOpportunity to work at a rapidly growing Voice AI startup, backed by top investors.Compensation and equity: Competitive salary package, additional benefits and stock options, enabling you to take part in the company’s success.Startup Culture: Dynamic, fast-paced environment with passionate and collaborative colleagues.High Impact: Groundbreaking startup at a pivotal growth stage, making a real difference in how people experience audio.Ownership & Autonomy: Take full ownership of projects and ship fast.Work With the Best: World-class team of engineers and builders with ample room for professional growth.Contribute to the Future: Define the landscape of Voice AI technology.If you are ready to lead the charge in revolutionizing Voice AI and drive our startup to new heights, we would love to hear from you. Apply today to join the ai-coustics team!Sourced from LinkedIn. Relocantly aggregates public job postings; apply on the original site.