Machine Learning Engineer II

Sorenson Communications is the industry leading provider of language services for the Deaf and hard-of-hearing. As a Machine Learning Engineer II, you will lead the productization of AI/ML research pipelines, transforming proof-of-concept models into robust, scalable systems while collaborating closely with AI scientists and software engineers.

Responsibilities:

• Own end-to-end productization of ML research pipelines, from proof-of-concept to production-grade systems, ensuring functional parity, reliability, and scalability
• Design and implement production ML inference pipelines, including preprocessing, model serving, and postprocessing stages, with a focus on low latency and throughput
• Architect scalable microservice-based or modular ML systems, making deliberate decisions around system design (e.g., monolith vs. microservices, synchronous vs. asynchronous processing)
• Build and maintain APIs and backend services (REST, gRPC, WebSocket) to support real-time and batch ML inference at scale
• Containerize ML model pipelines using Docker and deploy them on cloud platforms (AWS preferred), leveraging orchestration tools such as Kubernetes or ECS
• Implement MLOps best practices including CI/CD pipelines, automated testing, model versioning, and reproducible build environments
• Develop robust monitoring and observability tooling to track system health, model performance, latency, and data drift in production
• Ensure systems are secure and compliant, including model encryption at rest, TLS/mTLS traffic encryption, PII controls, and network egress restrictions
• Collaborate with research scientists to understand model requirements, manage dependencies, and coordinate handoffs from research to production
• Optimize ML model pipelines for inference efficiency using techniques such as quantization, batching, and hardware acceleration (GPU/CPU)
• Lead and mentor junior engineers on the team, driving technical decisions and code quality standards
• Document system architecture, software design decisions, and operational runbooks to ensure maintainability and knowledge transfer
• Other duties as assigned

Requirements:

• Minimum 4 Year / Bachelors Degree Bachelor's Degree in Computer Science, Computer Engineering, Mathematics, or a related field
• 5 Years of experience in software engineering with a focus on ML systems, MLOps, or production AI pipelines. A Master's degree may be considered equivalent to 2 years of experience. A PhD may be considered equivalent to 3 years of experience
• Strong proficiency in Python and experience with ML frameworks such as PyTorch and TensorFlow
• Demonstrated experience deploying and serving ML models in production environments, including familiarity with model serving runtimes such as Triton Inference Server, TorchServe, vLLM or equivalent
• Experience containerizing and orchestrating ML workloads using Docker and Kubernetes (or AWS ECS/EKS)
• Hands-on experience with cloud platforms, preferably AWS, including services such as ECS, EKS, S3, ECR, CloudWatch, and Lambda
• Strong understanding of software engineering principles including modular design, testability, and CI/CD pipeline development (e.g., GitHub Actions)
• Experience building APIs and backend services using REST, gRPC, or WebSocket protocols for real-time or streaming applications
• Familiarity with MLOps tooling and practices: experiment tracking, model versioning, pipeline orchestration (e.g., MLflow, DVC, Airflow, or equivalent)
• Experience with monitoring and observability tools such as AWS CloudWatch, Datadog, Prometheus, or Dynatrace
• Understanding of security best practices in ML systems: model encryption at rest, TLS traffic encryption, PII handling, and network access controls
• Experience with model optimization techniques for inference efficiency, such as quantization, pruning, batching, or ONNX export
• Ability to write comprehensive unit, integration, and load tests for ML-integrated systems
• Excellent communication and collaboration skills, with experience working across research and engineering teams
• Professional attitude, team player, good interpersonal communication skills and able to work across company departments
• Graduate Degree Master's or PhD in Computer Science, Machine Learning, or a related technical field
• Experience working with video, audio, or multimodal ML pipelines is a plus
• Experience with Infrastructure as Code tools such as Terraform is a plus