Senior AI Platform Engineer - Distributed Systems & MLOps

TetraScience, Inc.; Cambridge (MA); On-site; USD 170,000 - 220,000; Full time

Benefits offered by this job

Competitive compensation

Stock options

Employer-paid benefits

401(k)

Unlimited PTO

Flexible work arrangements

Life Insurance

Long-Term Disability

Job summary

TetraScience, Inc. is seeking a Senior Software Platform Engineer to design and run key parts of our AI and data infrastructure, working at the intersection of distributed systems and MLOps.

You will own major parts of the platform end-to-end, collaborating with Applied AI, data engineering, and platform teams to deliver cloud services for production AI/ML workflows. The role focuses on model and prompt lifecycle, RAG integration, security, observability, and multi-tenant safeguards within a

Qualifications

• Experience building and running distributed, cloud-native systems in production.
• Ownership of a significant service or component with focus on scalability and cost.
• Hands-on AI/ML infrastructure experience in production with model deployment lifecycle.
• Experience taking LLM-based systems to production with RAG, embeddings, and tooling calls.
• Security in a multi-tenant platform with PII/PHI handling and prompt-injection awareness.
• Strong coding skills in TypeScript and Python for APIs and backend services.
• Production experience with a model registry and serving stack (Databricks MLflow).
• APIs designed with REST/OpenAPI, scalable and versioned, secure.

Responsibilities

• Design, build, and operate services and APIs for models and agents on customer data.
• Own model and prompt lifecycle across Databricks MLflow and AWS Bedrock.
• Build inference paths for real-time and batch AI workloads with efficient routing and batching.
• Integrate LLMs into production with RAG, tool calls, and MCP tooling.
• Implement security guardrails and data boundaries across prompts, retrieval, and tools.
• Develop evaluation tooling, CI gates, drift detection, and quality metrics.
• Set up monitoring, logging, and distributed tracing; define SLIs/SLOs.
• Ensure reproducibility with versioned data, code, prompts, and artifacts.
• Write infrastructure as code (CloudFormation, CDK) and enable multi-tenant upgrades.
• Own production readiness, incident response, and runbooks; mentor engineers.
• Evaluate new frameworks and model providers; provide build-vs-buy guidance.

Skills

Distributed systems

TypeScript

Python

REST APIs

OpenAPI

AWS

Databricks MLflow

Docker

CDK/CloudFormation

Observability (SLI/SLO)

Tools

Databricks MLflow

AWS Bedrock

TensorFlow / PyTorch

Docker

CloudFormation

CDK

Job description

TetraScience, Inc. is seeking a Senior Software Platform Engineer to design and run key parts of our AI and data infrastructure, working at the intersection of distributed systems and MLOps.

You will own major parts of the platform end-to-end, collaborating with Applied AI, data engineering, and platform teams to deliver cloud services for production AI/ML workflows. The role focuses on model and prompt lifecycle, RAG integration, security, observability, and multi-tenant safeguards within a