Senior Software Engineer, On-Device Voice Reconstruction AI

Whispp; Leiden; On-site; EUR 90,000 - 135,000; Full time

Job summary

Whispp in Leiden is seeking a Senior Software Engineer to own the hands-on work of getting our on-device Voice Reconstruction SDK running on customer hardware, from PoC through production integration.

You will collaborate with AI researchers and product teams, drive integration playbooks for OEM programs, and push robustness across CPU/NPU targets while maintaining documentation. The role requires deep C/C++ expertise, Android experience, and strong collaboration with customer engineering teams.

Qualifications

• 6+ years in embedded, mobile platform, or systems engineering.
• Strong C/C++ for embedded or mobile platforms.
• Experience integrating AI/ML models on-device.
• Android platform engineering experience (Kotlin/Java).
• Familiarity with audio pipelines and real-time processing.
• Experience collaborating with customer engineering teams.

Responsibilities

• Integrate and validate the W2S SDK on customer devices and OS environments.
• Own PoC and NRE program execution: hardware setup, milestones, and scope docs.
• Identify and fix integration blockers across hardware and software.
• Keep demo hardware reliable for customer meetings and trade shows.
• Serve as the primary technical contact for OEM engineering teams.
• Translate customer constraints into concrete integration scopes.
• Support sales with technical depth on scoping calls and proposals.
• Improve SDK robustness across CPU and NPU targets.
• Develop repeatable integration playbooks and test harnesses.
• Provide feedback to the AI team from field findings.

Skills

C/C++ for embedded/mobile

Android (Kotlin/Java)

Edge AI inference

Security: TEEs/secure enclaves

Real-time audio processing

SDK development/integration

AOSP experience

Customer-facing collaboration

English fluency

Willing to travel

Tools

TFLite

ONNX Runtime

NPU/DSP acceleration tooling

Job description

Senior Software Engineer, On-Device Voice AI

About Whispp

Whispp is an award-winning deep-tech startup in Leiden. Our on-device Voice Reconstruction AI turns whispered, affected, and noisy speech into a person's clear, natural voice — in under 100 ms, on-device, with full speaker identity preserved. We license the technology as an SDK to smartphone and PC OEMs, chipset vendors, and hearing-protection manufacturers, and we have active proof-of-concept programs with tier-1 partners.

The role

You are the technical bridge between our AI platform and the OEM partners who embed it. You own the hands-on work of getting our SDK running on customer hardware, from first scoping call through validated PoC, signed NRE, and production integration.

This is our first dedicated integration hire. You'll work directly with our AI researchers, full-stack engineer, Technical Product Manager, and business development team — and set the technical foundations that let us run multiple OEM programs at once.

What you'll do

Integration and delivery

• Integrate and validate the W2S SDK on customer devices, chipsets, and OS environments — Qualcomm Snapdragon, PC NPUs, emerging hearable platforms.
• Own technical execution of PoC and NRE programs: hardware setup, milestones, KPI measurement, demos, and final scope documentation.
• Find and fix integration blockers early — hardware quirks, OS audio pipeline incompatibilities, latency and performance gaps.
• Keep demo hardware reliable and ready for customer meetings and trade shows.
• Act as the primary technical contact for OEM engineering teams during PoC, NRE, and validation.
• Translate customer constraints — microphone configurations, NPU limits, audio pipeline architecture — into concrete integration scopes.
• Back up the sales team with technical depth on scoping calls and in proposals.

Platform and tooling

• Improve SDK robustness and on-device execution across CPU and NPU targets.
• Build repeatable integration playbooks, test harnesses, and hardware setups that cut time-to-integration for each new OEM.
• Feed real-world findings — noise conditions, microphone behavior, latency, personalization edge cases — back to the AI team.
• Maintain integration documentation from v0.7 to v1.0 as the SDK and customer feedback evolve.

What we're looking for

• Strong C/C++ for embedded or mobile platform work.
• Android platform engineering in Kotlin/Java.
• Hands-on edge AI inference: NPU/DSP acceleration, TFLite, ONNX Runtime, or similar.
• Experience securing models on device — TEEs and secure enclaves on ARM and x86.
• Real-time audio processing, and solid grasp of Android audio pipelines (AudioReach, AudioRecord, AAudio, Oboe).
• SDK development or integration of third-party AI, audio, or DSP libraries into shipping products.
• AOSP experience is strong advantage.
• 6+ years in embedded, mobile platform, or systems engineering.
• Proven ability to work directly with customer engineering teams and document outcomes clearly.
• Fluent written and spoken English; Dutch is a bonus.
• Willing to travel to customer sites around 30% of the time.

Nice to have

• Speech processing, voice AI, or audio enhancement background.
• Work with Qualcomm, MediaTek, or ARM.
• Hearable, wearable, or hearing-protection integration.
• GDPR and on-device biometric data handling.
• Python for tooling and benchmarking.

Your first year

• Our Android SDK is integrated and validated on a smartphone OEM device, from PoC through NRE.
• Integration documentation hits v1.0 and speeds up onboarding for the next program.
• A second OEM integration is underway with clear milestones.
• Playbooks and templates are in place to support the Application Engineer hires planned for later in 2026.