MLOps / Infrastructure Engineer

Role overview

MLOps / Infrastructure Engineer (Remote, U.S.-based) You’ll build and operate infrastructure for a real-time ML-powered content moderation system that detects and triages abuse, threats, and edge-case language. The role is hands-on and sits at the intersection of machine learning, systems, and product delivery, partnering with ML engineers, researchers, and clients.

Responsibilities

• Design and maintain cloud infrastructure on GCP or AWS for:
  • real-time model serving
  • data ingestion and evaluation workflows
• Deploy and optimize APIs for low-latency ML model access and embedding search systems
• Manage the end-to-end training data flow (sourcing, cleaning, preparing for model consumption) with a focus on accuracy, scalability, and efficiency
• Build observability tooling for production ML pipelines (latency, error rates, request volumes, drift)
• Automate model deployment, retraining, and evaluation pipelines using CI/CD for ML
• Help package models for serving alongside ML engineers
• Manage and optimize vector databases and semantic search infrastructure (e.g., Pinecone, FAISS, Vertex Matching Engine)
• Ensure security, compliance, and uptime for safety-critical infrastructure

Requirements

• 3–8 years experience deploying ML systems or high-availability backend systems
• Shipped and maintained production infrastructure at scale, supporting ML workflows
• Experience with GCP, AWS, or similar platforms (including managed ML services)
• Proficient with Terraform, Docker, Kubernetes (or similar infrastructure tools)
• Understands performance tradeoffs for model serving and embedding search pipelines
• Ability to collaborate cross-functionally with ML, security, and product teams
• Builder mindset and comfort working in ambiguous environments

Nice to have

• Vector databases / ANN systems, ideally on GCP or AWS
• Experience serving LLMs or embedding-based models via API
• Monitoring/logging/metrics tools (e.g., Prometheus, Grafana, Sentry)
• Familiarity with trust & safety, abuse detection, or policy enforcement systems

First 3 months success criteria

• Deployed and monitored a real-time ML inference system with clear observability
• Implemented an API with <200ms latency for embedding/classifier inference
• Streamlined deployment and retraining workflows with ML engineers
• Built logging/monitoring to understand performance and classifier behavior

Compensation & benefits

• $130K–$230K base salary (dependent on experience and location)
• Performance-based annual bonus
• Professional development support (education, conferences, training)
• Fully remote, U.S.-based
• Comprehensive health, dental, and vision; generous PTO
• 401(k) retirement plan