Senior AI Platform Engineer - MLOps & Scalable Infra

TetraScience; United States; On-site; USD 200,000 - 270,000; Full time

Benefits offered by this job

Remote work

401K

Unlimited PTO

Life Insurance

LTD/STD

Career coaching

Competitive salary

Job summary

TetraScience is seeking a Lead Software Platform Engineer to own and scale its AI/ML platform in a cloud-native, multi-tenant environment. You will own architecture, model lifecycles, and production readiness, collaborating with Applied AI, data engineers, and platform teams.

You will design the inference substrate, integrate LLMs, ensure security at scale, and drive observability, cost control, and CI/CD automation for enterprise pharma-grade workloads.

Qualifications

• 10+ years of software and infrastructure engineering, with distributed, cloud-native systems in production.
• Experience as a technical leader or architect responsible for design decisions, scalability, performance, and cost.
• Security-focused design for multi-tenant platforms, including PII/PHI handling and prompt-injection awareness.
• Hands-on experience deploying AI/ML infrastructure in production, multi-tenant products, and latency considerations.
• Proficiency in API-first design, REST/OpenAPI, and secure scalable interfaces.

Responsibilities

• Own the technical architecture of the AI/ML platform and its API surface.
• Manage the end-to-end model and prompt lifecycle across Databricks MLflow and AWS Bedrock.
• Design the inference substrate for real-time and batch AI workloads, including GPU planning.
• Integrate LLMs and agent runtimes with platforms and applications.
• Design security, guardrails, and data boundaries across prompts and retrieval.
• Build eval harnesses, regression gates, and drift monitoring for production models.
• Establish observability with SLI/SLO/SLA, logging, and tracing for probabilistic outputs.
• Contribute to IaC and deployment automation (CloudFormation, CDK).

Skills

Distributed systems

Cloud-native

Technical leadership

API design

Mentoring

AWS

Tools

TypeScript

Python

Databricks MLflow

AWS CDK

Docker

Job description

TetraScience is seeking a Lead Software Platform Engineer to own and scale its AI/ML platform in a cloud-native, multi-tenant environment. You will own architecture, model lifecycles, and production readiness, collaborating with Applied AI, data engineers, and platform teams.

You will design the inference substrate, integrate LLMs, ensure security at scale, and drive observability, cost control, and CI/CD automation for enterprise pharma-grade workloads.