Machine Learning Operations Engineer

Propio is on a mission to make communication accessible to everyone. As a leader in real‑time interpretation and multilingual language services, we connect people with the information they need across language, culture, and modality. We’re committed to building AI‑powered tools to enhance interpreter workflows, automate multilingual insights, and scale communication quality across industries.Role SummaryThe Machine Learning Operations Engineer will design, build, and maintain the production infrastructure required to deploy, scale, monitor, and govern Propio’s ML and agentic AI systems. This role ensures that translation, speech, interpretation, and conversational AI models run reliably, securely, and cost‑effectively in real‑time environments. The MLOps Engineer bridges ML engineering, DevOps, and platform engineering—owning the end‑to‑end operational lifecycle from training pipelines to automated deployment to observability, aligning with HIPAA, SOC2, and HITRUST standards.Key ResponsibilitiesBuild and maintain scalable model serving infrastructure for real‑time inference (translation, ASR/TTS, agentic AI workflows)Implement automated CI/CD pipelines for ML models and LLM agents, including versioning, rollback strategies, and multi‑environment promotion (dev, staging, prod)Develop GPU/compute orchestration strategies for cost‑efficient workloads across AWS (SageMaker, ECS/EKS, EC2, or Databricks)Implement reproducible ML workflows with strong dependency management, data lineage, feature versioning, and reproducibility guaranteesIntegrate observability platforms (Datadog, MLflow, LangSmith) for end‑to‑end tracing of agentic workflows and multi‑step tool executionBuild alerting systems and dashboards for both business‑level metrics (quality, throughput) and engineering metrics (GPU load, memory, queue depth)Ensure ML systems meet HIPAA, SOC2, and HITRUST standards, including encryption, audit logging, access controls, and secure handling of PHIImplement data validation, schema enforcement, and drift detection to guarantee data quality for both training and inferenceManage model registry, feature store, and lineage tracking across all AI servicesWork closely with Machine Learning Engineers to productionize models and agentic systems, ensuring seamless handoff from experimentation to deploymentCollaborate with Data Engineering to operationalize data pipelines feeding ML/LLM workflowsPartner with DevOps, Security Engineering, and Platform Engineering to integrate ML systems into Propio’s cloud stackOptimize model serving architectures for latency, concurrency, and costImplement autoscaling, caching, routing, and load‑balancing solutions for high‑volume LLM and speech‑based systemsEvaluate and implement new technologies (vector databases, real‑time streaming infra, model compression, quantization)Requirements3+ years of experience in ML Ops, DevOps, or ML platform Engineering or similar infrastructure‑focused ML rolesStrong experience with AWS (SageMaker, EKS/ECS, Lambda, Step Functions, S3, IAM), Databricks, or equivalent cloud ecosystemsStrong proficiency with ML lifecycle tools: MLflow, Kubeflow, SageMaker Pipelines, Airflow, Prefect, or equivalentStrong foundations in CI/CD, containerization (Docker), orchestration (Kubernetes), and infrastructure‑as‑code (Terraform, CloudFormation)Experience implementing monitoring and observability for ML systems (Datadog, Prometheus/Grafana, LangSmith, MLflow)Familiarity with securing ML pipelines and handling regulated data under HIPAA and SOC2Proficiency in Python and experience supporting ML engineers in productionizing ML/LLM workflowsBachelor’s or Master’s in Computer Science, Software Engineering, ML/AI, or related field#J-18808-Ljbffr