Senior Machine Learning Engineer, Recommendation & Growth

ByLabs; San Francisco (CA); In loco; USD 150.000 - 230.000; Tempo pieno

Descrizione del lavoro

ByLabs in San Francisco is seeking a Senior Machine Learning Engineer to advance a fast-moving personalization stack across multiple live scenarios. You will own and optimize large-scale recommendation systems for Web and mobile, driving stateful models and real-time feature pipelines.

You will lead development in generative recommendations, sequential modeling, and multi-objective optimization, while shaping ML infrastructure and collaborating with cross-functional teams.

Competenze

• 5+ years of industry experience in recommendation or growth algorithms at consumer-scale internet companies.
• Deep knowledge of two-tower models, sequential models, multi-objective modeling, and reinforcement learning.
• Experience building high-throughput real-time feature pipelines (Kafka/Flink) enabling minute-level updates; contribution to a unified online/offline Feature Store.
• Proficiency in Python and at least one JVM or compiled language (Java, Scala, Go, C++); experience with ML frameworks (PyTorch, TensorFlow, or JAX) and big data tools (Hive SQL, Spark, Flink, or MapReduce).

Mansioni

• Own the optimization of a large-scale recommendation system across trading product discovery, content feeds, and community content ranking for Web and mobile users.
• Lead personalization model development and iteration across multiple directions—generative recommendation, user sequential modeling, and multi-objective modeling.
• Build growth intelligence systems for churn prediction, upgrade propensity, reactivation likelihood, and LTV prediction models.
• Build the ML infrastructure and model research layer for interactive recommendation and AI-powered personalization, powering real-time ranking and retrieval systems.
• Partner with Growth Product, Data Science, and engineering teams to define success metrics, translate business goals into ML system requirements, and mentor junior engineers.

Conoscenze

Two-tower models

Sequential models

Multi-objective modeling

Reinforcement learning

Python

Java/Scala/Go/C++

Strumenti

Kafka

Flink

Spark

MapReduce

PyTorch

TensorFlow

JAX

Hive SQL

Faiss/Milvus/HNSW

Descrizione del lavoro

As as a Senior Machine Learning Engineer, you will join a team that has already proven it can move fast at scale — our personalization system operates across 13 live scenarios. Your job is to take this foundation to the next level.

Key Responsibilities

• Own the optimization of large-scale recommendation system, delivering personalized experiences across trading product discovery, content feeds, and community content ranking for Web and mobile users.
• Lead personalization model development and iteration across multiple directions — including generative recommendation, user sequential modeling, and multi-objective modeling — while exploring multi-scenario joint modeling to unify user signals across trading, community, and campaign surfaces.
• Build growth intelligence systems, applying causal inference and other advanced methods to develop churn prediction, upgrade propensity, reactivation likelihood, and LTV prediction models.
• Build the ML infrastructure and model research layer for interactive recommendation and AI-powered personalization, powering real-time ranking and retrieval systems.
• Partner closely with Growth Product, Data Science, and engineering teams to define success metrics, translate business goals into ML system requirements, and ship measurable business impact; define engineering standards, lead design reviews, and mentor junior engineers as the team scales.

Major Requirements

• 5+ years of industry experience in recommendation or growth algorithms at consumer-scale internet companies; deep knowledge of two-tower models, sequential models, multi-objective modeling, and reinforcement learning.
• Build high-throughput real-time feature pipelines (Kafka/Flink) enabling minute-level user behavioral feature updates; contribute to a unified online/offline Feature Store architecture, governing feature consistency and eliminating time-travel leakage across training and serving.
• Own the construction and optimization of large-scale vector retrieval systems (Faiss/Milvus/HNSW) supporting candidate pools scaling from thousands to millions of heterogeneous items (trading products, news, KOL content, on-chain signals).
• Strong proficiency in Python and at least one JVM or compiled language (Java, Scala, Go, C++); experience with ML frameworks (PyTorch, TensorFlow, or JAX); proficiency in big data tools (Hive SQL, Spark, Flink, or MapReduce).

Nice-to-have:

• Hands-on experience with large-scale data infrastructure: Kafka, Spark/Flink, Redis, feature stores, and online serving systems.
• Experience in crypto/Web3 or fintech with strong understanding of user behavior in financial contexts; experience with LLM-based personalization or generative recommendation architectures; experience in multi-scenario joint modeling (unifying signals across search, recommendation, and marketing); experience with LTV prediction, operations research, or subsidy/budget optimization.
• Experience building recommendation systems for social/community platforms; publications at top AI/ML venues (KDD, NeurIPS, WWW, SIGIR, WSDM, CIKM, ICLR, ICML).