Lead AI Platform Engineer (Remote) – MLOps & Scale

TetraScience; Cambridge (MA); On-site; USD 200,000 - 270,000; Full time

Benefits offered by this job

Employer-paid benefits

Unlimited PTO

401K

Remote-friendly options

Life Insurance

Coaching and career development

Job summary

TetraScience is seeking a Lead Software Platform Engineer to own and scale our AI/ML data infrastructure as a product used by scientists worldwide. You will architect cloud-based services and MLOps infrastructure that enable production-grade AI/ML workflows, collaborating with Applied AI, data engineers, and platform teams.

You will guide the technical design authority for models, LLMs, and agents, ensuring secure, cost-efficient, and scalable deployment in a regulated environment.

Qualifications

• 10+ years of professional software and infrastructure engineering across distributed, cloud-native systems.
• Proven track record as a technical leader or architect responsible for system design, scalability, performance, and cost optimization.
• Experience designing security into a multi-tenant platform, including data boundaries and prompt injection risks.
• Hands-on experience deploying AI/ML infrastructure in production as a multi-tenant product with external users.

Responsibilities

• Own the technical architecture of the AI/ML platform and the service surface customers use to run models.
• Oversee end-to-end model and prompt lifecycle, including versioning and multi-model serving.
• Design inference substrate for real-time and batch workloads with routing, batching, and caching.
• Integrate LLMs and retrieval-augmented generation; architect agent runtimes and tool calling.
• Incorporate security, guardrails, and data privacy across prompts, retrieval, and tool calls.
• Build eval and quality infrastructure with CI gates, A/B testing, and drift detection.
• Establish observability, SLI/SLO/SLA, and runbooks for production readiness.
• Ensure reproducibility and regulatory audit trails with versioned data and artifacts.
• Contribute to IaC and deployment automation (CDK, CloudFormation).
• Provide SME guidance, lead design reviews, and mentor engineers on distributed AI systems.
• Set direction on emerging AI infrastructure and build-versus-buy decisions.

Skills

Distributed systems

MLOps

Cloud-native

Architecture leadership

AI infrastructure

Reliability engineering

API-first design

Python

TypeScript

Tools

Databricks MLflow

AWS Bedrock

OpenAPI

REST

CDK

CloudFormation

Job description

TetraScience is seeking a Lead Software Platform Engineer to own and scale our AI/ML data infrastructure as a product used by scientists worldwide. You will architect cloud-based services and MLOps infrastructure that enable production-grade AI/ML workflows, collaborating with Applied AI, data engineers, and platform teams.

You will guide the technical design authority for models, LLMs, and agents, ensuring secure, cost-efficient, and scalable deployment in a regulated environment.