ML Engineer — Production-Scale, Low-Latency Inference

Evlo AI; San Diego (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Evlo AI is seeking an ML Engineer to own the design, training, and production deployment of scalable machine learning systems—from experimentation notebooks to low-latency inference services handling real traffic daily.

This hands-on role sits at the intersection of applied research and production software engineering, requiring strong Python expertise and experience with cloud ML platforms to ship reliable models quickly and safely.

Qualifications

• 3–7 years of experience in ML engineering with multiple models taken from prototype to production
• Strong Python engineering skills; proficiency with PyTorch, TensorFlow, or XGBoost in production settings
• Hands-on experience with cloud ML platforms and infrastructure: AWS SageMaker, GCP Vertex AI, or equivalent Kubernetes-based serving
• Deep understanding of ML fundamentals: evaluation methodology, regularization, class imbalance, and leakage prevention
• Experience with workflow orchestration and data tooling: Airflow, dbt, Spark, Kafka, or equivalent
• B.S. or M.S. in Computer Science, Statistics, or a related quantitative field (or equivalent practical experience)
• Bonus: experience fine-tuning LLMs or optimizing transformer inference; contributions to open-source ML tooling; prior work in high-scale, low-latency serving environments

Responsibilities

• Design, train, and evaluate ML models — classification, ranking, forecasting, and NLP — for use cases that directly drive product outcomes
• Build and maintain feature pipelines in Python and PySpark, ensuring training/serving consistency and data quality across environments
• Deploy and version models using AWS SageMaker, Vertex AI, or Kubernetes-based serving stacks, including canary rollouts and rollback strategies
• Instrument production models for data drift, latency, and performance regression with automated monitoring and alerting pipelines
• Optimize inference performance: quantization, batching, caching, and GPU utilization for latency-sensitive workloads
• Collaborate with data scientists and product engineers to translate ambiguous problem statements into scoped, testable ML solutions
• Contribute to MLOps maturity: CI/CD for models, experiment tracking (MLflow or W&B), and reproducible training pipelines

Skills

Python engineering

ML model development

Production deployment

Data modeling

Education

B.S./M.S. in CS or related field

Tools

PyTorch

TensorFlow

XGBoost

AWS SageMaker

GCP Vertex AI

Kubernetes

Airflow

dbt

Spark

Kafka

MLflow

Weights & Biases

Job description

Evlo AI is seeking an ML Engineer to own the design, training, and production deployment of scalable machine learning systems—from experimentation notebooks to low-latency inference services handling real traffic daily.

This hands-on role sits at the intersection of applied research and production software engineering, requiring strong Python expertise and experience with cloud ML platforms to ship reliable models quickly and safely.