🛠 Tech Stack

💼 About This Role

You'll build scalable, low-latency ML inference platforms for personalization, search, and content understanding at Tubi. You'll improve deployment and operations, lead cross-functional projects, and transform ML capabilities. This role offers architectural freedom to explore new frameworks.

🎯 What You'll Do

• Design and build scalable, high-throughput, low-latency distributed systems using Scala.
• Build reusable components for ML applications like Personalization, Search, and Ads.
• Partner with ML engineers to develop scalable solutions for their challenges.
• Optimize latency, cost, and efficiency of ML infrastructure through data-driven analysis.

📋 Requirements

• Experience designing and building scalable distributed systems with a modern backend language (e.g., Scala, Java, Python, Go, C++).
• Strong experience with AWS or equivalent cloud platform.
• Experience building online microservices at scale with low latency serving.
• Experience with SQL/NoSQL databases, message brokers, and caches (e.g., Postgres, Cassandra, Kafka, Redis).

✨ Nice to Have

• Familiarity with ML inference engines (e.g., TorchServe, Triton, vLLM) and vector stores (e.g., LanceDB, FAISS).
• Experience with Recommender Systems, Search, Autocomplete, or Ads ML.
• Proficiency in data-driven analysis of complex A/B testing results.

🎁 Benefits & Perks

• 💵 Annual bonus and long-term incentive plan.
• 🏥 Medical/dental/vision insurance and 401(k) plan.
• 🏖️ Flexible Time Off policy for salaried employees.
• 👶 12 weeks paid parental leave for bonding after birth/adoption.
• 💪 Monthly wellness reimbursement.