> Markdown version of [/jobs/ext/3011780-machine-learning-engineer-graduate-e-commerce-recommendation-video-2027-start](https://www.wearedevelopers.com/jobs/ext/3011780-machine-learning-engineer-graduate-e-commerce-recommendation-video-2027-start). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Machine Learning Engineer Graduate (E-Commerce Recommendation Video) - 2027 Start - **Company:** Tiktok Inc - **Location:** San Jose, CA, United States - **Experience:** Starter - **Salary:** $128,000.0 - $316,800.0 - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Neural Networks, Big Data, C++ (Programming Language), Encodings, Data Structures, Linux, Distributed Computing Environment, Information Retrieval, Python (Programming Language), Machine Learning, Recommender Systems, Tensorflow, SQL Databases, Pytorch, Apache Spark, Deep Learning, Information Technology, Apache Flink, Machine Learning Operations - **Published:** September 20, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=e0baaf2cd80fa844 ## About the Role * Individuals who are completing or have recently completed a Bachelor's degree in Computer Science, Electrical Engineering, Mathematics, Statistics or a related discipline. * Solid algorithms and data-structures fundamentals and excellent coding ability: clean, efficient, reproducible code. * Solid foundations in machine learning, probability, and statistics: you understand the assumptions behind a model and where it breaks, and you can explain why a method works and under what conditions it fails - not just how to call the API. * Fluent in a deep-learning framework (PyTorch / TensorFlow) and at least one large-scale data-processing tool (Spark / Flink / SQL); proficient in Python, with working C++ and Linux skills. * Data sense and experimental rigor: you can locate the real cause behind a metric movement, and you understand A/B test design, statistical confidence, and the common pitfalls. * Fast learner, clear communicator, good collaborator., * Research or engineering experience in recommendation, search, ads, information retrieval, NLP, or large-scale ML systems. * Publications at KDD, NeurIPS, WWW, SIGIR, WSDM, ICML, ICLR, RecSys, CIKM, or comparable venues - or high-quality open-source contributions. * Awards in Kaggle, Tianchi, or RecSys Challenge, or an ACM-ICPC / NOI competition background. * Hands-on experience with causal inference, online learning / bandits, graph neural networks, sequence modelling, or large-scale distributed training. * Heavy user of AI coding and agentic workflows for building systems and optimizing models., Qualified applicants with arrest or conviction records will be considered for employment in accordance with all federal, state, and local laws including the Los Angeles County Fair Chance Ordinance for Employers and the California Fair Chance Act. Our company believes that criminal history may have a direct, adverse and negative relationship on the following job duties, potentially resulting in the withdrawal of the conditional offer of employment ## Description * Optimize the recommendation models across the full funnel: You own the models behind TikTok Shop's product, short-video, and livestream recommendation - retrieval, pre-ranking, ranking, re-ranking, and multi-queue blending - and every iteration ships to real traffic. Core threads: * Ranking and retrieval models. Iterate the model architectures that carry the funnel: multi-task and multi-objective learning from click through conversion and GMV; multi-scenario, multi-format joint modelling; and the sample, label, and debiasing design that decides what the model actually learns. * User interest modelling. Ultra-long behavior sequences (10K+ events) with real trade-offs between positional-encoding extrapolation, attention cost, and online latency and storage; decoupling stable preferences from seasonal demand, momentary impulses, and needs already satisfied; and mining implicit negative feedback - impressions without clicks, consecutive skips, fast swipes - at every stage of the funnel. * Multimodal representation learning. Combine product images, text, and video content with behavioural data into high-quality item and user representations. * Re-ranking, blending, and exploration. List-level decisions rather than pointwise scores: multi-queue blending across content types, diversity and repetition control, and exploration mechanisms that surface interests users have not yet expressed - while breaking the recommendation feedback loop. * Design the cold-start and content-ecosystem mechanisms: New products, new livestream hosts, and new creators arrive in volume every day. * Do original work on open problems. Long-term value modelling, repurchase and retention, transaction attribution, fatigue modelling, new-user recommendation, incremental value modelling, LLM4Rec - the frontier problems of a real recommendation system, where the industry has no standard answers. ## Related Videos - [Alibaba Big Data and Machine Learning Technology](https://www.wearedevelopers.com/videos/37-alibaba-big-data-and-machine-learning-technology) - [Docker network without Docker](https://www.wearedevelopers.com/videos/1418-docker-network-without-docker) - [Photonic Computing: Programming a New Class of AI Accelerators (incl. Live Coding)](https://www.wearedevelopers.com/videos/100196-photonic-computing-programming-a-new-class-of-ai-accelerators-incl-live-coding) - [How We Built a Machine Learning-Based Recommendation System (And Survived to Tell the Tale)](https://www.wearedevelopers.com/videos/752-how-we-built-a-machine-learning-based-recommendation-system-and-survived-to-tell-the-tale) - [Docker exec without Docker](https://www.wearedevelopers.com/videos/1094-docker-exec-without-docker) - [Data Science in Retail](https://www.wearedevelopers.com/videos/586-data-science-in-retail) ## Related Articles - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models) - [How machine learning can help us tell fact from fiction](https://www.wearedevelopers.com/magazine/509-how-machine-learning-can-help-us-tell-fact-from-fiction) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Highest Paying Tech Companies for Developers](https://www.wearedevelopers.com/magazine/220-highest-paying-tech-companies-for-developers) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift)