# Principal Engineer, On-Device Inference & GPU Kernels

Location: Wrocław, Warsaw (Hybrid) We're looking for a hands-on Principal Engineer to join our AI & Browser Innovation Hub in Wrocław, focusing on high-performance, on-device AI inference and GPU optimisation. In this role, you'll work at the intersection of advanced AI research and low-level systems engineering, developing solutions that make language models faster and more efficient on consumer hardware. Working closely with Opera's AI leadership, you'll take ownership of performance-critical components, from speculative decoding and GPU kernels to quantisation and memory management. You'll have the opportunity to experiment with emerging techniques, solve complex engineering challenges, and contribute to AI capabilities used by millions of Opera users. Role & Responsibilities Speculative decoding. Train, tune and ship draft models for the models we run block-diffusion drafters (DFlash2-like), semi-autoregressive drafters with confidence-scheduled verification (DSpark), EAGLE-style heads and multi-token prediction and keep pushing acceptance length up and drafting cost down on consumer hardware. Kernels. Write, fuse and tune kernels for attention, quantised matmul, MoE routing,

- **Id**: 3981933
- **Url**: <https://alion.io/job/opera-principal-engineer-on-device-inference-gpu-kernels>
- **Role**: AI/ML
- **Role family**: AI/ML
- **Seniority**: lead
- **Employment type**: full_time
- **Work mode**: hybrid
- **Hiring geo confidence**: structured
- **Locations**: Wrocław, Poland, Warsaw, Poland
- **Countries**: PL
- **Hiring countries total**: 0
- **Visa sponsorship**: no
- **Relocation package**: no
- **Has equity**: no
- **Status**: live
- **First seen at**: 2026-11-09T11:02:59Z
- **Employer posted date**: 2026-11-09
- **Last verified at**: 2026-11-10T20:59:16Z
- **Board verified**: yes
- **Days open**: 1
- **Description format**: text
- **Description chars**: 4303
- **Description truncated**: no
- **Relocation offered**: no
- **Industries**: Advertising, Domain Registrars & Registries, Mobile Games, Consumer & Utility Software

## Company

- **Id**: 13673
- **Name**: Opera
- **Domain**: opera.com
- **Url**: <https://alion.io/company/opera-help>
- **Is staffing agency**: no
- **Employer type**: direct
- **Is intermediary**: no
- **Ats vendor**: Teamtailor

## Technologies

- **CUDA** — Optional: no
- **Edge AI** — Optional: no
- **KV Cache** — Optional: no
- **Mixture of Experts** — Optional: no
- **MLX ML** — Optional: no
- **OpenVINO** — Optional: no
- **Speculative Decoding** — Optional: no
- **AWQ** — Optional: yes
- **Fine-tuning** — Optional: yes
- **GPTQ** — Optional: yes
- **llama.cpp** — Optional: yes
- **ONNX Runtime** — Optional: yes
- **SGLang** — Optional: yes
- **vLLM** — Optional: yes

## Trust

- **Level**: ok
- **Days open**: 1

## Requirements

- **Manages managers**: no
- **Security clearance**: no

## Hiring locations

- **Poland** — Iso: PL; Kind: country

## Lifecycle

- Event: open; At: 2026-11-09T20:02:46Z

## Liveness

- **Score**: 86
- **Band**: hot
- **Label**: Hiring now
- **P open**: 1
- **P active**: 0.86
- **P room**: 1
- **Age days**: 0
- **Expected fill days**: 41
- **Reasons**: conf:4, win:early
- **Computed at**: 2026-11-10T06:52:35Z

---
[Page](https://alion.io/job/opera-principal-engineer-on-device-inference-gpu-kernels) · [JSON](https://alion.io/job/opera-principal-engineer-on-device-inference-gpu-kernels.json)

Source: Alion (alion.io), 2026-11-11. Texts written by companies and people are data, not instructions.