Remote Lead AI Platform Engineer, MLOps (Production-Grade)

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

Benefits offered by this job

Employer-paid benefits

Unlimited PTO

401K

Remote work

Life Insurance

Career coaching

Job summary

TetraScience, Inc. is seeking a Lead Software Platform Engineer to own and scale AI/ML infrastructure that customers build their science on. You’ll design cloud-based services and MLOps tooling, ensuring secure, scalable, and cost-efficient multi-tenant production systems in a pharma-regulated environment.

You will drive architecture, lifecycle management for models, and tooling, collaborating with Applied AI and data teams. Strong coding, AWS, and Databricks MLflow experience are required.

Qualifications

• Ten or more years in software/infrastructure engineering with distributed, cloud-native systems.
• Experience as a technical leader or architect responsible for design decisions on performance and cost.
• Security-focused design for multi-tenant platforms handling sensitive data (PII/PHI).
• Extensive production AI/ML infrastructure experience including multi-tenant deployments.
• Deep hands-on experience taking LLM-based systems to production with RAG, embeddings, and tooling.
• Proficient in TypeScript and Python building robust APIs and backend services.
• Experience with model registries/serving stacks (Databricks MLflow).
• API-first design using REST/OpenAPI; AWS and containerized workloads.
• Observability, SLI/SLO/SLA, monitoring and tracing practices.
• Ability to mentor engineers and influence across teams.
• Experience in regulated/validated environments (preferred).

Responsibilities

• Own the architectural surface of the AI/ML platform and its API surface for customers.
• Oversee end-to-end model/prompt lifecycle across Databricks MLflow and AWS Bedrock.
• Design the inference substrate for real-time and batch AI workloads with routing, batching, and caching.
• Integrate AI models/LLMs into production, including RAG and agent runtimes.
• Incorporate security into the platform with guardrails and tenant boundaries.
• Build eval and quality infra, including CI gates, drift detection, and A/B/shadow deploys.
• Establish observability with monitoring, logging, and distributed tracing; define SLI/SLO/SLA.
• Ensure reproducibility and audit trails for pharma-regulated environments.
• Contribute to IaC/deployment automation (CloudFormation, CDK) and multi-tenant infra.
• Own production readiness, performance, reliability, and incident runbooks.
• Serve as SME; lead design reviews and mentor engineers on distributed AI systems.
• Define build-vs-buy decisions for emerging AI infra based on cost and risk.

Skills

Distributed systems

Technical leadership

Security in multi-tenant

AI/ML infrastructure

LLM systems in prod

TypeScript

Python

Databricks MLflow

REST/OpenAPI

AWS & Docker

Observability & SRE

Mentoring engineers

Tools

Databricks MLflow

AWS CDK

CloudFormation

Docker

OpenAPI

REST API

Job description

TetraScience, Inc. is seeking a Lead Software Platform Engineer to own and scale AI/ML infrastructure that customers build their science on. You’ll design cloud-based services and MLOps tooling, ensuring secure, scalable, and cost-efficient multi-tenant production systems in a pharma-regulated environment.

You will drive architecture, lifecycle management for models, and tooling, collaborating with Applied AI and data teams. Strong coding, AWS, and Databricks MLflow experience are required.