Principal ML Ops Engineer
Pragmatike5 months ago
Cambridge, MA, USAStaff+
Responsibilities
- Architect, build, and scale end-to-end ML Ops pipelines for training, fine-tuning, evaluation, rollout, and monitoring.
- Design reliable infrastructure for model deployment, versioning, reproducibility, and orchestration across cloud and on-premises GPU clusters.
- Optimize compute usage across distributed systems through Kubernetes, autoscaling, caching, GPU allocation, and checkpointing workflows.
- Implement observability for ML systems, including monitoring of drift, performance, throughput, reliability, and cost.
- Build automated workflows for dataset curation, labeling, feature pipelines, evaluation, and ML model deployment.
- Collaborate with researchers to productionize models and accelerate training and inference pipelines.
- Establish ML Ops best practices, internal standards, and cross-team tooling.
- Mentor engineers and influence architectural direction across the AI platform.
Requirements
- Deep hands-on experience designing and operating production ML systems at scale, with Staff/Principal-level experience expected.
- Strong background in ML Ops, distributed systems, and cloud infrastructure including AWS, GCP, or Azure.
- Proficiency with Python and familiarity with TypeScript or Go for platform integration.
- Expertise with PyTorch, Transformers, vLLM, Llama-factory, Megatron-LM, and CUDA/GPU acceleration.
- Strong experience with Docker, Kubernetes, Helm, and autoscaling.
- Deep understanding of ML lifecycle workflows including training, fine-tuning, evaluation, inference, and model registries.
- Ability to lead technical strategy, collaborate cross-functionally, and work in a fast-paced environment.
- Experience deploying and operating LLMs and generative models in production at enterprise scale is a bonus.
- Familiarity with DevOps, automated deployment pipelines, infrastructure-as-code, GPU cluster optimization, scheduling, distributed training frameworks, data engineering, feature pipelines, or real-time ML systems is preferred.
- Startup experience or comfort with ambiguity and high ownership is preferred.
- English is required.
Benefits
- Relocation package available for Cambridge, MA applicants.
- Remote option available for out-of-state applicants.
- Competitive salary and equity options.
- Sign-on bonus.
- Health, dental, and vision benefits.
- 401(k).
Categories
About Pragmatike
Pragmatike is a Paris-based IT services and recruiting firm connecting remote-first companies with software engineers and tech specialists worldwide. Founded in 2022, it places contractors or full-time hires and staffs teams to complete projects for startups and scaleups. The private partnership offers access to a large network of 50,000+ specialists across 60+ countries.