Senior AI Infrastructure Engineer

Summary

Join TetraScience, a leader in Scientific Data and AI Cloud, as a Senior AI Infrastructure Engineer. Design, build, and scale AI and data infrastructure, focusing on cloud-based MLOps pipelines. Collaborate with AI engineers, data engineers, and platform teams. Maintain and improve the performance, reliability, and cost-efficiency of AI models. Contribute to the design and evolution of the AI platform. Integrate AI models and LLMs into production systems. This role requires extensive experience in AI/ML infrastructure and strong coding skills.

Requirements

• 7+ years of professional experience in software engineering and infrastructure engineering
• Extensive experience building and maintaining AI/ML infrastructure in production, including model, deployment, and lifecycle management
• Strong knowledge of AWS and infrastructure-as-code frameworks, ideally with CDK
• Expert-level coding skills in TypeScript and Python building robust APIs and backend services
• Production-level experience with Databricks MLFlow, including model registration, versioning, asset bundles, and model serving workflows
• Proven ability to design reliable, secure, and scalable infrastructure for both real-time and batch ML workloads
• Ability to articulate ideas clearly, present findings persuasively, and build rapport with clients and team members
• Strong collaboration skills and the ability to partner effectively with cross-functional teams

Responsibilities

• Design, implement, and maintain cloud-native infrastructure to support AI and data workloads, with a focus on AI and data platforms such as Databricks and AWS Bedrock
• Build and manage scalable data pipelines to ingest, transform, and serve data for ML and analytics
• Develop infrastructure-as-code using tools like Cloudformation, AWS CDK to ensure repeatable and secure deployments
• Collaborate with AI engineers, data engineers, and platform teams to improve the performance, reliability, and cost-efficiency of AI models in production
• Drive best practices for observability, including monitoring, alerting, and logging for AI platforms
• Contribute to the design and evolution of our AI platform to support new ML frameworks, workflows, and data types
• Stay current with new tools and technologies to recommend improvements to architecture and operations
• Integrate AI models and large language models (LLMs) into production systems to enable use cases using architectures like retrieval-augmented generation (RAG)

Preferred Qualifications

• Familiarity with emerging LLM frameworks such as DSPy for advanced prompt orchestration and programmatic LLM pipelines
• Understanding of LLM cost monitoring, latency optimization, and usage analytics in production environments
• Knowledge of vector databases / embeddings stores (e.g., OpenSearch) to support semantic search and RAG

Benefits

• 100% employer-paid benefits for all eligible employees and immediate family members
• Unlimited paid time off (PTO)
• 401K
• Flexible working arrangements - Remote work
• Company paid Life Insurance, LTD/STD
• A culture of continuous improvement where you can grow your career and get coaching