Overview
Senior Machine Learning Engineer to independently lead end-to-end ML model development and delivery within a programmatic DSP, from problem framing and pipelines through training, evaluation, deployment, and monitoring.
What you'll do
- Lead development of complex ML models for campaign selection and conversion prediction.
- Design and own scalable evaluation frameworks using offline metrics, backtesting, and online A/B analysis.
- Own end-to-end deployment of models and tools, including rollback plans and monitoring.
- Implement real-time monitoring to detect performance degradation and trigger responses.
- Improve inference latency while maintaining model performance.
- Coordinate cross-functional rollouts of model and architectural changes and protect production stability with guardrails and staged rollouts.
- Mentor junior ML contributors via code reviews, pairing, and structured guidance.
What you'll need
- 4–7 years of professional machine learning experience including end-to-end model development, deployment, and production monitoring.
- Bachelor’s or Master’s degree in Mathematics, Physics, Computer Science, or a related technical field.
- Experience leading complex model development with measurable business impact.
- Proficiency in Python and SQL, plus hands-on experience with big data tools (Spark) and ML libraries.
- Strong ML techniques experience including regression, classification, ranking, gradient-boosted trees, and neural architectures.
- Experience designing evaluation frameworks and diagnosing training/serving gaps, feature drift, and data quality issues.
- Strong grasp of probability, statistics, and experimental design including A/B testing and causal reasoning.
Nice to have
- Experience with system programming languages (C++, Rust) and contributing to the inference layer.
- Hands-on experience with online inference systems, gRPC/REST model endpoints, or streaming feature pipelines (Kafka/Flink).
- Ad-tech domain knowledge including auction dynamics and fraud detection.
- Experience with contextual bandits, multi-armed bandit frameworks, or reinforcement learning in production.
- Familiarity with MLOps tooling such as MLflow, Prefect/Airflow, and model registries.
Details
Read the full description and apply on the company’s own careers page.
NewPosted yesterday
