ML Ops Engineer

About us

Pass App is on a mission to ignite financial freedom and true ownership for people everywhere. Each member of our team takes ownership and contributes a unique piece to our journey into the exciting realm of web3. Together, we craft more than just meaningful products and services—we create a lasting tangible impact in the real world.

We want you to join our search for greatness at the edge of what is technologically possible. Are you tired of the ordinary? Crave a challenge that sparks passion and purpose? We’d love to have you apply!

The role you’re applying for

As we aim to simplify the web3 experience, enhance user engagement through personalized recommendations, and take our users along in this journey of web3 awareness, we are leveraging cutting-edge AI technology to build a scalable web3 solution that abstracts away all the underlying complexity. With the expansion of our AI capabilities, we’re looking to onboard a ML Ops Engineer to build cutting-edge AI/ML solutions in the emerging field of Web3, enhancing user engagement with personalized smart wallet features. You will play a key role in building our recommendation systems and AI-assistant.

What you’ll be doing

• Deploy and manage machine learning models for real-time recommendation systems and AI agents within the company’s smart wallet platform.
• Build robust, scalable, and low-latency ML deployment pipelines to handle real-time Web3 data streams.
• Optimize ML model inference times and integrate them seamlessly with APIs and backend systems.
• Design and maintain monitoring systems to evaluate deployed model performance and data drift.
• Collaborate with data scientists to convert experiments into production-grade solutions.
• Implement and maintain CI/CD pipelines for continuous model updates.
• Research and evaluate ML frameworks and tools for scalable deployment in a cloud-based environment.

What we’re looking for

• 5-7 years of experience working with ML deployment tools and frameworks like MLflow.
• Proficiency in Kubernetes, Docker, and cloud platforms such as AWS, GCP, or Azure.
• Expertise in API development and microservices for seamless ML integration.
• Knowledge of distributed computing for large-scale ML model deployment.
• Familiarity with model optimization techniques like quantization and pruning.
• Strong programming skills in Python, with experience in REST and GraphQL APIs.

Nice to have:

• Exposure to blockchain and Web3 technologies, especially handling on-chain/off-chain data for AI use cases.

We got you covered

Working remotely is more than just a benefit or a perk. We believe in the power of remote work to unleash creativity and passion. Join our globally remote team with 35+ different nationalities and enjoy the flexibility to work from anywhere in the universe. As long as you are available in the European working timezone.

Join our team and pursue your passions on your own terms, while we provide you with a competitive compensation package including attractive “crypto-native” bonuses, learning and development budgets, personal development plans and team retreats to fuel your web3 curiosity.