Senior Machine Learning Engineer (Biometrics & Face Recognition)

Scandit; Zürich; Hybrid; CHF 140,000 - 180,000; Full time

Benefits offered by this job

Hackathons

Flexible work—office, hybrid or home

Equity program

People-first culture

Great Place to Work

Job summary

Scandit in Zurich is looking for a Senior Machine Learning Engineer to own the face-matching models for high assurance identity verification. You will ship on-device, collaborating with C++ engineers to run on millions of phones and scanners.

You will drive data collection, evaluation, and model integration, while exploring liveness and anti-spoofing techniques to ensure secure user verification.

Qualifications

• 5+ years as an ML engineer with production models
• Hands-on experience with biometrics: face recognition/verification
• Experience with liveness or PAD in security contexts

Responsibilities

• Design, train and evaluate face detection/recognition models for ID portraits
• Support liveness and PAD against spoofs and deepfakes
• Define quality metrics, benchmarks and test sets for high assurance
• Own data collection, labeling, prototyping, training, evaluation and integration
• Optimise on-device inference with C++ engineers
• Mentor ML engineers on practice

Skills

Biometrics

Face recognition

Face verification

Liveness/PAD

Python

PyTorch

ONNX

C++ on-device

iOS/Android

Model deployment

Tools

ONNX Runtime

Core ML

TFLite

On-device SDK

Job description

Scandit gives people superpowers. Whether enabling delivery drivers to make quicker deliveries, matching a patient with their medication, or allowing retailers to make store operations more efficient, our technology automates workflows. It provides actionable insights to help businesses in a variety of industries. Join us as we continue to expand, grow, innovate, and help take Scandit to the next level.

Banks, fintechs and regulated businesses need more than document scanning. They need to know the person holding the ID is real and is its rightful owner. As a Senior Machine Learning Engineer in our ID Capture team, you will build the machine learning behind that, centred on face recognition and face matching. You will also support our liveness and presentation attack detection work.

You will have real ownership of the architecture, data and benchmarks, and your models will run fully on device, on the phones our users already have, with no cloud round-trip.

If these challenges sound interesting to you, we'd love to hear from you!

About the role

You will drive our face-matching work for high-assurance identity verification. You will own models end to end and work closely with our C++ engineers to ship them on device, at scale, on millions of phones and scanners.

What you will do

• Design, train and evaluate models for face detection, face recognition and 1:1 face matching against ID document portraits
• Support the team's work on liveness and presentation attack detection (PAD) against spoofs, replays and deepfakes
• Define quality metrics, benchmarks and test sets that meet high-assurance and regulatory expectations
• Own the full loop: data collection and labelling strategy, prototyping, training, evaluation, debugging and model integration
• Optimise models for on-device inference with our C++ engineers (quantisation, pruning, mobile runtimes)
• Track research in biometrics and face anti-spoofing, and turn it into product direction
• Mentor engineers on ML practice

Our tech stack

• Python, PyTorch
• ONNX
• C++ on-device SDK
• iOS / Android

Who you are

We are looking for an experienced ML engineer who has shipped production models to real users and has worked hands-on with biometrics. You are comfortable owning ambiguous problems, moving fast and then iterating. You also work well with product, C++ and QA engineers.

• 5+ years as an ML engineer, with production models shipped to real users
• Hands-on experience with biometrics: face recognition, face verification, liveness or PAD
• Fluent in Python and at least one deep learning framework (PyTorch preferred)
• Strong grasp of evaluation for security-sensitive systems: FAR/FRR, bias and fairness across demographics, adversarial robustness
• Clear communicator who works well across disciplines
• Eligible to work in the hiring location

Nice to have:

• Knowledge of standards such as ISO/IEC 30107 (PAD), NIST FRTE/FATE or iBeta testing
• Experience deploying models on mobile or edge (TFLite, ONNX Runtime, Core ML)
• Working knowledge of C++

What we offer

Here are just some of the reasons why people choose to build their careers at Scandit:

• A highly skilled team and a fun environment where you can put your enthusiasm for cutting-edge technologies to use
• Hackathons
• Flexible, office, hybrid or home working
• People-first culture
• Global team outings, Micro Adventures
• Festive/end of year all company celebrations
• Your birthday off
• An attractive individual equity plan in a high growth company
• We are certified as a "Great Place to Work" in 7 countries!
• Excellent office infrastructure, optimized for hybrid working in Zurich, Warsaw, Tampere, and London
• Excellent support for remote work across Switzerland, Finland, Poland, UK, Italy and Germany
• Specific benefits related to the location you are joining

At Scandit we strive to create an inclusive environment that empowers our employees. We believe that our products and services benefit from our diverse backgrounds and experiences and are proud to be a safe space for all.

All qualified applicants will receive consideration for employment without regard to race, color, nationality, religion, sexual orientation, gender, gender identity, age, physical [dis]ability or length of time spent unemployed.

Imagine the What. Build the How.

#engineering