Senior Machine Learning Engineer

Edison Smart®; San Francisco (CA); Hybrid; USD 315,000 - 385,000; Full time

Job summary

Edison Smart® is standing up a new US R&D center in the San Francisco Bay Area and seeks a lead ML engineer to own the full-stack recommendation and growth ML direction end to end. You will build models and infrastructure for personalized trading product discovery, campaign targeting, and content ranking for a platform with 80M+ users.

You will collaborate with Growth Product, Data Science, Community, and regional teams to set engineering standards and mentor the US team as it grows.

Qualifications

• 5+ years in ML engineering, recommendation systems, or growth engineering at a consumer-scale internet company.
• Proven track record shipping real-time recommendation or personalisation systems to millions of users.
• Solid knowledge of collaborative filtering, two-tower models, sequential models, GNNs, multi-objective modeling, and contextual bandits/RL.
• Strong Python and at least one JVM/compiled language; experience with PyTorch/TensorFlow/JAX and big data tooling.
• Hands-on with large-scale data infrastructure: Kafka, Spark/Flink, feature stores, online serving.
• Some grounding in AI/Agent work and cross-timezone collaboration; fluent English and Mandarin.

Responsibilities

• Design and build low-latency, real-time recommendation systems across web and mobile.
• Own the full ML lifecycle from data prep to production deployment.
• Apply advanced personalisation techniques across trading, community, and campaign surfaces.
• Develop predictive models for churn, upgrade propensity, and LTV with causal inference.
• Architect and own the full-stack A/B experimentation infrastructure.

Skills

ML engineering

Recommendation systems

Python

JVM languages

PyTorch/TensorFlow/JAX

Big data tooling

Real-time systems

A/B testing

English-Mandarin bilingual

Tools

Kafka

Spark

Flink

Redis/Cassandra

Feast/Tecton

Job description

Up to $350k base salary + Bonus + Equity.

Salary can be open for the right engineer.

San Francisco, Bay Area (Remote or Hybrid)

About the Role

Our client is standing up a new US R&D center and needs someone to own the full-stack recommendation and growth ML direction end to end, not a slice of the pipeline, the whole system. You'll build the models and infrastructure that personalise trading product discovery, campaign targeting, content feeds, and community content ranking for a platform with 80M+ users, while also shaping how AI and agent-based approaches get folded into that stack.

Duties

• Design and build low-latency, real-time recommendation systems across web and mobile — owning the full ML lifecycle from data prep and feature engineering through training, evaluation, and production deployment
• Apply advanced personalisation techniques (two-tower retrieval, sequential models, GNNs, multi-objective modeling with PLE/MMoE, contextual bandits) across trading, community, and campaign surfaces, with an eye toward unifying signals across them
• Build the personalisation layer for the client's AI investment assistant: integrate portfolio signals, trading behaviour, on-chain data, and market intelligence into real-time token recommendations, market alerts, and eventually autonomous agent-driven investment workflows
• Develop predictive models for churn, upgrade propensity, reactivation, and LTV, applying causal inference (uplift modeling, difference-in-differences) to optimise intervention timing and subsidy allocation
• Build a full user lifecycle data and value system — behavioural signals predicting key conversion milestones, personalised intervention strategies, and rigorous treatment-effect measurement
• Architect and own the full-stack A/B experimentation infrastructure: assignment, metric pipelines, statistical frameworks (CUPED, sequential testing), and self-serve tooling
• Build and maintain real-time and batch feature pipelines, partnering with data engineering on feature store design and end-to-end observability
• Partner with Growth Product, Data Science, Community, and Asia-Pacific engineering teams to translate business goals into ML requirements; set engineering standards and mentor as the US team grows

Target Candidates

This is a lead-from-the-front role for someone who has run recommendation at scale before and wants to build the function — and the team — from the ground up, bringing engineering philosophy and best practice from a top-tier tech company with them.

• 5+ years in ML engineering, recommendation systems, or growth engineering at a consumer-scale internet company
• Proven track record shipping real-time recommendation or personalisation systems to millions of users; strong knowledge of collaborative filtering, two-tower models, sequential models, GNNs, multi-objective modeling, and contextual bandits/RL
• Solid foundation in causal inference and statistical learning: uplift modeling, A/B experiment design, treatment effect estimation
• Strong Python plus at least one JVM/compiled language (Java, Scala, Go, C++); experience with PyTorch/TensorFlow/JAX and big data tooling (Hive SQL, Spark, Flink)
• Hands-on with large-scale data infrastructure: Kafka, Spark/Flink, feature stores (Feast, Tecton, or equivalent), online serving (Redis, Cassandra)
• Some grounding in AI/Agent work — understands where recommendation systems and LLMs are converging, and has hands-on Agent-related engineering experience (anomaly detection, skill/tool integration) that can be fused with recommendation capability
• Fluent in English and Mandarin, able to bridge the US R&D center with Asia-Pacific engineering and product teams in Singapore, Dubai, and beyond (comfortable with occasional early-morning/evening cross-timezone meetings)