AI Operations Engineer

About the Role

Join our dynamic ML/AI team to take cutting-edge models from prototype to production, building robust data pipelines and ensuring seamless service operation.

Responsibilities

• Design and maintain CI/CD pipelines for ML model training, packaging, and deployment.
• Manage containerized services on AWS ECS, optimizing for cost, latency, and availability.
• Automate infrastructure provisioning and service configuration with Terraform.
• Maintain and scale services that utilize third-party LLM providers.
• Build and improve data pipelines from BigQuery, S3, and DynamoDB into training and inference workflows.
• Instrument services with observability tooling (Datadog, OpenTelemetry, Langfuse) and establish SLOs.
• Collaborate with ML engineers to productionize new models using BentoML, FastAPI, and container-based serving.

Requirements

• 2-3 years in ML Ops supporting ML/AI features, systems, and workflows, with 3-4 years prior experience in DevOps, CloudOps, or SRE.
• Strong proficiency in Python.
• Hands-on experience with Docker containerization and orchestration.
• Solid understanding of CI/CD for ML workflows in an enterprise production environment.
• Experience with Infrastructure as Code, preferably Terraform.
• Familiarity with AWS (ECS, ECR, S3, DynamoDB, CloudWatch) and GCP (BigQuery, Vertex AI).
• Experience with LLM integration and observability (OpenAI API, Google GenAI, Langfuse tracing).
• Experience building and maintaining data pipelines for ML training and feature engineering.

Nice-to-Haves

• Familiarity with ML modeling workflows (training, evaluation, experiment tracking, model versioning).
• Experience monitoring and flagging model drift.
• Exposure to NLP/NLU models and frameworks (Hugging Face Transformers, spaCy).
• Knowledge of vector databases (LanceDB, FAISS) and embedding-based retrieval systems.
• Experience with scaling and maintaining deep learning frameworks (TensorFlow, PyTorch) in production.
• Familiarity with classical ML libraries (scikit-learn, XGBoost) and model explainability tools (SHAP).
• Working knowledge of ML serving frameworks such as BentoML.
• Comfort working with FastAPI or similar async Python web frameworks.