๐ง๐ต๐ถ๐ ๐ฟ๐ผ๐น๐ฒ ๐ถ๐ ๐ณ๐ผ๐ฟ ๐ผ๐ป๐ฒ ๐ผ๐ณ ๐๐ต๐ฒ ๐ช๐ฒ๐ฒ๐ธ๐ฑ๐ฎ๐'๐ ๐ฐ๐น๐ถ๐ฒ๐ป๐๐
๐ฆ๐ฎ๐น๐ฎ๐ฟ๐ ๐ฟ๐ฎ๐ป๐ด๐ฒ: ๐ฅ๐ ๐ฎ๐ฑ๐ฌ๐ฌ๐ฌ๐ฌ๐ฌ - ๐ฅ๐ ๐ด๐ฑ๐ฌ๐ฌ๐ฌ๐ฌ๐ฌ (๐ถ๐ฒ ๐๐ก๐ฅ ๐ฎ๐ฑ-๐ด๐ฑ ๐๐ฃ๐)
Experience: 4+ yrs
Location: NCR, Delhi, India
As a Senior ML Engineer, you will lead the design and deployment of cuttingโedge recommendation and personalization solutions that drive user engagement across our digital ecosystems. You will collaborate closely with data scientists, product managers, and engineering teams to build highโthroughput, lowโlatency recommendation engines that adapt in real time to user behavior and contextual signals. By leveraging graph-based matchโscoring, sophisticated ranking models, and innovative coldโstart strategies, you will enhance the relevance of content and product suggestions for millions of users worldwide. Your work will directly influence key metrics such as clickโthrough rate, conversion rate, and user retention, while ensuring scalability, robustness, and maintainability of the underlying machine learning infrastructure.
Requirements
๐๐ฒ๐ ๐ฅ๐ฒ๐๐ฝ๐ผ๐ป๐๐ถ๐ฏ๐ถ๐น๐ถ๐๐ถ๐ฒ๐
โขDesign, develop, and productionโgrade realโtime recommendation pipelines that process millions of events per day.
โขEngineer graphโbased matchโscoring algorithms to uncover latent userโitem relationships and improve match quality.
โขBuild and fineโtune ranking models using learningโtoโrank, gradientโboosted trees, or deep neural network approaches.
โขDevelop coldโstart solutions for new users and items using hybrid collaborative filtering, content embeddings, and transfer learning.
โขPerform feature engineering at scale, ensuring feature freshness, consistency, and low latency latency requirements.
โขCollaborate with data engineering teams to optimize data ingestion, storage, and retrieval for recommendation workloads.
โขConduct rigorous A/B testing, statistical analysis, and interpret model outputs to drive dataโdriven decisions.
โขMentor junior ML engineers, sharing best practices, code review, and debugging techniques.
โขStay abreast of industry research, publish findings, and iterate on emerging techniques such as reinforcement learning or multiโarmed bandit frameworks.
โขEnsure robust monitoring, logging, and alerting for model drift, latency, and error rates across all services.
๐ช๐ต๐ฎ๐ ๐ ๐ฎ๐ธ๐ฒ๐ ๐ฌ๐ผ๐ ๐ฎ ๐๐ฟ๐ฒ๐ฎ๐ ๐๐ถ๐
โข4+ years of handsโon experience building largeโscale recommendation systems in a production environment.
โขDeep expertise in personalization, ranking, and realโtime recommender architectures.
โขStrong background in graph theory, graph neural networks, and bipartite graph matching for recommendation tasks.
โขProven track record of addressing coldโstart challenges with innovative techniques and measurable impact.
โขProficiency in Python, SQL, Spark/Databricks, and a major cloud platform (AWS, GCP, Azure).
โขSolid experience with ML frameworks such as TensorFlow, PyTorch, LightGBM, and XGBoost.
โขDemonstrated ability to translate metrics and business objectives into actionable ML solutions.
โขExcellent communication skills, capable of presenting complex technical concepts to nonโtechnical stakeholders.
โขA collaborative mindset, comfortable working in crossโfunctional teams in a fastโpaced, iterative environment.
โขPassion for staying current with academic research and industry trends, and willingness to experiment with new ideas.