Senior Machine Learning Engineer (MLops and Infra Focus)

We know it, you know it. Most companies ramble on about purpose and making the world a better place. And pretty often it feels a bit… well, forced. But we’d like to think that our story is special for real.

Our founders, Shadi Bitar and Ninos Malki, came to Sweden from Syria when they were kids. Books became their compass, guiding them through the maze of life, and helping them shape their destinies in a new world.

Their dream was bold: What if they could unlock the world of books for everyone, making knowledge and inspiration accessible to all? Fast forward a few years, and the tale of Nextory was born.

At Nextory, we've crafted a revolutionary monthly subscription that empowers our users to devour books like never before, be it through reading or listening. It's not just a product; it's a passport to endless adventure and enlightenment.

WHY THIS ROLE MATTERS

We’re scaling our AI capabilities to help millions of users find their next favorite book. To do that, we need someone to help build the infrastructure behind:

📚 Personalized recommendations
🤖 AI librarian, our multi-agentic book recommender with chat interface
🔍 Semantic search with LLMs and vector retrieval

This isn’t just about training models - it’s about designing systems that deliver them reliably, efficiently and at scale.

WHAT YOU WILL DO 

⚫️ Ship ML-powered features to production with real user impact

⚫️ Diagnose and triage issues: analyze logs, core dumps, and diagnostic data to identify root causes and drive timely resolutions.

⚫️ Build and scale ML infrastructure on Google Cloud Platform (Vertex AI, BigQuery, GCS)

⚫️ Develop production-quality Python services to serve models across chat, search, and recommendation systems

⚫️ Strong experience with Google Cloud’s Python SDKs, with a preference for deep familiarity with Vertex AI service

⚫️ Implement MLOps practices including model versioning, drift detection, and evaluation tooling

⚫️ Drive CI/CD, observability, and automation for ML workflows

⚫️ Ensure model serving is low-latency, scalable, and cost-efficient

OUR STACK 🧰 

Languages: Python, SQL

Cloud & MLOps: GCP (Vertex AI, BigQuery), Vertex AI Pipelines

Search & Retrieval: Vertex AI Search

Infra & Observability: Docker, Kubernetes, Terraform, GCP Monitoring

SKILLS AND QUALIFICATIONS

⚫️ 5+ years in ML or backend engineering, with 3+ in production-grade ML infra

⚫️ Proficient in Python, with experience deploying cloud-native ML systems (preferably GCP + Vertex AI)

⚫️ Deep experience with end-to-end ML pipelines (training, serving, evaluation) and model serving via REST APIs

⚫️ Strong command of Kubernetes, CI/CD, and infrastructure as code

⚫️ Able to mentor engineers, perform code reviews, and drive architectural decisions

⚫️ Comfortable with SQL and working with large datasets

⚫️ Experience managing large-scale pipelines with solid observability practices

⚫️ Strong problem-solving and communication skills; thrives in iterative, fast-paced environments

⚫️ You’re collaborative, pragmatic, and care about impact more than ego

BONUS IF YOU HAVE 🌟

Experience with Recommendation systems , LLM-based features, or vector search

Hands-on experience with natural language processing (NLU and NLG)

Hands-on experience with (multi-)agent systems

Familiarity with Vertex AI Search and RAG pipelines

A passion for metadata tracking, model governance, or responsible ML