ML Engineer
CodeRound is hiring for this role.
- Machine Learning
- ML Engineer
- Recommendation Systems
- Recommender Systems
- Personalization
- Ranking
- Search
- Feed Ranking
- Matchmaking
- Machine Learning
- Deep Learning
- User Embeddings
- Two-Tower Models
- Learning to Rank
- Collaborative Filtering
- Vector Search
- ANN Search
- Graph Algorithms
- LLM
- Cold Start
- Real-Time ML
- MLOps
- A/B Testing
- B2C
- Consumer Tech
- Social
- Dating
- Ecommerce
We are looking for an ML Engineer to build the core recommendation, ranking, and personalisation systems powering a next-generation matchmaking and relationship platform. You’ll work on a real-time ML recommendation engine that learns from user interactions and behavioural signals, owning the lifecycle from modelling and experimentation through production deployment. This is a hands-on role at the intersection of recommendation systems, personalisation, embeddings, ranking, and real-time ML infrastructure.
What you'll do
- Design, build, and deploy matchmaking, recommendation, ranking, and personalisation systems
- Develop a real-time adaptive recommendation engine that learns from user interactions and other behavioural signals
- Build ranking algorithms that deliver highly personalised and curated user experiences
- Develop user embeddings, similarity models, and graph-based match-scoring frameworks
- Research and implement cold-start solutions for users and recommendations with limited data
- Experiment with collaborative filtering, deep retrieval, learning-to-rank, embeddings, ANN search, and LLM-based approaches
- Own the full lifecycle of recommendation models, from problem definition and modelling to deployment and monitoring
- Establish and improve offline and online evaluation frameworks, A/B tests, and recommendation metrics
- Deploy models to production using fast iteration loops, model registries, and observability tooling
- Collaborate closely with Data, Product, and Backend teams to translate ML capabilities into strong customer experiences
- Help build the foundation for scalable, real-time ranking and recommendation infrastructure
Must have
2–4 years of experience working on recommendation systems, personalisation, search, feed ranking, or related ML problems at scale Strong hands-on experience building recommendation, ranking, or personalisation models Experience with a B2C product, ideally in social, ecommerce, fashion, dating, gaming, video, or other consumer platforms Understanding of recommendation techniques such as collaborative filtering, learning-to-rank, embeddings, similarity models, and retrieval systems Experience with end-to-end ML pipelines, including model development, experimentation, and/or production deployment Strong understanding of offline and online evaluation, A/B testing, and metric alignment Ability to work cross-functionally with Data, Product, and Backend teams Strong understanding of ML fundamentals and ability to translate product problems into scalable ML solutions
Good to have
Experience with deep retrieval models, particularly two-tower architectures Experience with ANN/vector search and user/item embeddings Experience building graph-based recommendation or match-scoring systems Experience with LLM-based approaches for sparse-data or cold-start personalisation Experience solving cold-start recommendation problems Experience with real-time/adaptive recommendation systems Familiarity with model registries, ML observability, and production ML infrastructure Experience designing or deploying low-latency ranking/recommendation systems Prior experience owning or leading recommendation, feed ranking, search, or personalisation initiatives