Senior AI Platform Engineer — Production-Grade MLOps

TetraScience, Inc.; Cambridge (MA); Hybrid; USD 200,000 - 270,000; Full time

Benefits offered by this job

Employer-paid benefits

Unlimited PTO

401K

Remote work

Life Insurance

Professional growth

Job summary

TetraScience, Inc. is seeking a Lead Software Platform Engineer to own the AI and data infrastructure used by scientists worldwide. You will architect cloud-based services and MLOps capabilities, enabling production-grade AI/ML workflows and multi-tenant scalability.

You will work with Applied AI engineers, data engineers, and platform teams to design the model lifecycle, security, and observability, while guiding architectural decisions and mentoring engineers across the organization.

Qualifications

• Proven experience designing, building, and scaling distributed, cloud-native systems.
• Technical leadership or architect role with responsibility for design decisions, scalability, performance and cost.
• Experience embedding security into multi-tenant platforms, including data protection and prompt-injection awareness.
• Hands-on AI/ML infrastructure in production, lifecycle management, and multi-tenant product delivery.

Responsibilities

• Own the technical architecture of the AI/ML platform and its API surface for customer use.
• Manage end-to-end model lifecycle and multi-model serving across integration stacks.
• Design real-time and batch inference substrates, including routing, batching, and resource planning.
• Integrate LLMs and agent runtimes with platform-level tool calling and MCP-based tooling.
• Ensure security, guardrails, PII/PHI handling, and tenant data boundaries across prompts and retrieval.

Skills

Distributed systems

MLOps

TypeScript

Python

Databricks MLflow

AWS

APIs (REST/OpenAPI)

Security

Tools

Databricks MLflow

AWS

Job description

TetraScience, Inc. is seeking a Lead Software Platform Engineer to own the AI and data infrastructure used by scientists worldwide. You will architect cloud-based services and MLOps capabilities, enabling production-grade AI/ML workflows and multi-tenant scalability.

You will work with Applied AI engineers, data engineers, and platform teams to design the model lifecycle, security, and observability, while guiding architectural decisions and mentoring engineers across the organization.