Machine Learning Engineer - Python/LLM

Job Title : Machine Learning Engineer Recommendation Systems

Role Overview :

We are looking for a passionate and experienced Machine Learning Engineer to join our core recommendation team. In this role, youll lead the design and deployment of real-time personalization and matchmaking systems that power our user experience. From developing intelligent recommendation models to implementing production-grade infrastructure, you will be at the forefront of shaping a highly adaptive and scalable recommendation engine.

Key Responsibilities :

Model Development :

- Design, develop, and optimize systems for recommendations, feed ranking, personalization, and matchmaking.

Algorithm Innovation :

- Build user embedding systems, similarity models, graph-based algorithms, and cold-start solutions to enhance personalization.

Real-Time Personalization :

- Create adaptive systems that learn and evolve in real-time based on user interactions and behavioral signals.

End-to-End Ownership :

- Own the full ML lifecycle from problem formulation, model training, evaluation, deployment, and monitoring.

System Design :

- Develop scalable infrastructure and pipelines for feature engineering, ANN (Approximate Nearest Neighbors) search, model versioning, and model observability.

Cross-Functional Collaboration :

- Work closely with Product, Data, and Backend Engineering teams to deliver a deeply personalized and engaging user experience.

Model Evaluation :

- Use robust evaluation techniques including offline validation, online experiments (A/B testing), and long-term engagement metric tracking.

Requirements :

Experience :

- 37 years of hands-on experience building and deploying large-scale ML systems in recommendation, search, personalization, or ranking.

Domain Expertise :

- Prior experience working on B2C platforms such as e-commerce, dating, social, gaming, or video streaming applications.

Technical Skills :

- Strong programming skills in Python (or equivalent), with experience using libraries like TensorFlow, PyTorch, Scikit-learn, Faiss, etc.

- Experience with collaborative filtering, deep learning (two-tower or DSSM), embedding-based retrieval, learning-to-rank, and LLMs for personalization.

- Experience deploying ML models in production environments with CI/CD, model registries, and inference optimization.

- Knowledge of vector databases, graph-based algorithms, and retrieval-augmented generation (RAG) is a plus.

Machine Learning Ops :

- Proficient in building end-to-end ML pipelines using tools like MLflow, Kubeflow, Airflow, or similar.

- Experience with online inference at scale, including latency optimization, real-time data ingestion, and observability tooling.

Data Handling :

- Strong skills in working with large-scale structured and unstructured datasets and real-time streaming data.

Analytical Skills :

- Solid understanding of offline metrics (Precision@K, Recall, MAP, NDCG) and ability to set up and interpret A/B testing for recommender systems.

Nice to Have :

- Experience with graph neural networks (GNNs) or graph-based match scoring frameworks.

- Knowledge of LLM-based recommender architectures and their applications to sparse or cold-start scenarios.

- Exposure to LLM orchestration using tools like LangChain, LlamaIndex, or RAG for personalization tasks.

- Familiarity with edge inference, multi-armed bandits, or reinforcement learning-based recommendations.