Senior Production ML Engineer – Deploy & Scale

Immersum; Greater London; Hybrid; GBP 90,000 - 130,000; Full time

Job summary

Immersum in London is seeking a Senior Machine Learning Engineer to own production-ready ML systems, deploy models, and build end-to-end pipelines. You will collaborate with a senior data scientist to turn notebooks into scalable services, APIs, and batch or streaming inference, ensuring reliability and cost efficiency.

You’ll shape the approach, work across the data platform, monitor drift, retraining triggers, and maintain feature pipelines, with emphasis on performance, latency, and

Qualifications

• 5+ years hands-on experience deploying and operating ML models in production.
• Proven experience building model-serving infrastructure, monitoring and retraining pipelines end to end.
• Strong software engineering skills to turn data science code into production-ready systems.
• Experience managing operational challenges of ML workloads in real-world environments.
• Working knowledge of cloud data warehouses, ideally Snowflake.
• Comfortable working with data scientists, making engineering trade-offs autonomously.

Responsibilities

• Build and maintain production ML deployment and serving infrastructure, including APIs and batch or streaming inference.
• Develop model versioning, experiment tracking and safe deployment processes.
• Implement monitoring for model performance and drift, including retraining triggers and alerting.
• Build and maintain feature engineering pipelines, ensuring training/production consistency.
• Translate data science models and notebooks into robust, production‑grade code.
• Optimise compute, latency and cost across training and inference workloads.
• Own CI/CD processes for model deployment and testing.
• Evaluate ML tooling and make pragmatic build‑versus‑buy decisions.
• Support the underlying data platform, including Snowflake administration and pipeline maintenance.
• Provide technical guidance to colleagues as the data function develops.

Skills

ML deployment

Model serving infrastructure

CI/CD for ML

Python

Snowflake

Cloud data warehouses

Monitoring & retraining pipelines

Tools

Snowflake Cortex

Cortex Code

MLFlow

APIs

Job description

Immersum in London is seeking a Senior Machine Learning Engineer to own production-ready ML systems, deploy models, and build end-to-end pipelines. You will collaborate with a senior data scientist to turn notebooks into scalable services, APIs, and batch or streaming inference, ensuring reliability and cost efficiency.

You’ll shape the approach, work across the data platform, monitor drift, retraining triggers, and maintain feature pipelines, with emphasis on performance, latency, and