Machine Learning Engineer - E-Commerce Recommendation

Build the recommendation engine behind Tik Tok Shop LIVE. This onsite role in Seattle focuses on designing and shipping an end-to-end machine learning recommendation stack for live commerce, where model quality must meet strict latency and compute constraints. You'll work across large recommendation modeling, multimodal and generative retrieval, reward modeling and post-training, and agentic optimization tied to long-term value.

What you'll get includes competitive pay (base salary range $207,480 - $368,220 annually for the selected city), plus benefits such as day one medical, dental, and vision insurance, a 401(k) savings plan with company match, paid parental leave, disability coverage, and life insurance. You'll also have wellbeing benefits, 10 paid holidays per year, 10 paid sick days per year, and 17 days of Paid Personal Time (prorated upon hire with increasing accruals by tenure).

Additional discretionary bonuses/incentives may apply, and eligible employees may receive restricted stock units.

• Scale Large Recommendation Models (LRM) by pushing unified ranking foundation model capacity using sparse MoE, ultra-long user sequences, pre-training, and teacher-student distillation.
• Translate offline scaling gains into online wins under latency and compute budgets using dynamic compute allocation and on-device real-time inference.
• Build generative recommendation using multimodal Semantic IDs
  , combining visual, speech, text, collaborative, and product signals, including what is showcased, pinned, or auctioned in a live room, and serving near-real-time semantic .
• Apply LLM4
  
  Rec and multimodal LLM modeling to unify live rooms, short videos, and products in a single semantic space, transfer interests across content, search, and shopping, and address cold start for new creators, products, and markets.
• Develop reward models and post-training for conversion, long-term value, and user experience, aligning generative recommenders with SFT and DPO/GRPO-style RL post-training using generator-evaluator decoding and listwise objectives.
• Design Agent x Recommendation systems that auto-tune multi-objective value weights and traffic mechanisms, run and interpret experiments, and move from hand-tuned heuristics toward agentic optimization and multi-step RL.
• Optimize for long-term value and ecosystem health using LTV, uplift, and multi-touch attribution, while balancing short-term GMV with user experience and a healthy, growing creator ecosystem.
• Own the work end to end
  , from problem framing and data pipelines to large-scale training, online serving, A/B testing, and launch, partnering closely with engineering, product, and data science.

• Bachelor's degree or above in Computer Science, Electrical Engineering, Mathematics, Statistics
  , or related field.
• 3+ years of industry experience in recommendation, search, advertising, or other large-scale applied machine learning, with a record of models shipped and impacting online metrics.
• Strong machine learning fundamentals and hands-on depth in at least one:
  retrieval and ranking
  , sequential user modeling
  , multi-task learning
  , generative recommendation
  , or LLM/multimodal modeling
  .
• Proficiency in Python and/or C++, with solid experience in PyTorch or Tensor Flow
  , including distributed training and model optimization.
• Ability to turn ambiguous business problems into modeling solutions and to own iteration from offline experiments to online A/B results.

Python, C++, PyTorch, Tensor Flow

Live commerce may be the hardest recommendation problem  
Global E-commerce Recommendation Live Algorithm team owns the end-to-end recommendation stack for Tik Tok Shop LIVE
, spanning retrieval and pre-ranking through ranking, mixed ranking, and long-term value modeling.

One unified stack serves seven core surfaces across public discovery and private follower relationships. The team is rebuilding this system around foundation models, including large recommendation models that follow scaling laws, generative retrieval on multimodal semantic IDs, multimodal LLMs that connect content and commerce, reward models with RL post-training aligned to long-term value, and AI agents that tune and evolve the system alongside the team.

What is shipped directly drives GMV, buyer growth, and creator success for Tik Tok Shop in the US and across global markets.

Location: Seattle, WA (onsite).
Job Code: A254886.

Pay transparency: The base salary range for this position in the selected city is…