Senior AI Platform Engineer — Production ML Infra

TetraScience; San Mateo (CA); On-site; USD 170,000 - 220,000; Full time

Benefits offered by this job

Competitive compensation

Stock options

Employer-paid benefits for employees &

401(k)

Unlimited PTO

Flexible working arrangements

Company-paid Life Insurance

Job summary

TetraScience is hiring a Senior Software Platform Engineer to shape the AI cloud for biopharma. You will design, build, and operate critical services and APIs enabling external researchers to run models on their own data at scale, with strong emphasis on cost, latency, and security.

You will own major parts of the AI platform end-to-end, collaborating with Applied AI and data engineering teams to deploy production-grade workflows, improve observability, and drive platform direction through

Qualifications

• 7+ years of professional software/infrastructure engineering in distributed, cloud-native systems.
• Experience owning a significant service's design for scalability, performance, and cost.
• Hands-on AI/ML infra in production, including model deployment and lifecycle management for external users.

Responsibilities

• Design, build, and operate services and APIs for models and agents against scientific data.
• Own the model and prompt lifecycle across Databricks MLflow and AWS Bedrock.
• Build the inference path for real-time and batch AI workloads with routing, batching, and caching.
• Integrate LLMs into production systems using retrieval-augmented generation (RAG).
• Ensure platform security with guardrails and data boundaries.

Skills

TypeScript

Python

Distributed systems

ML/AI infrastructure

MLOps

AWS

Databricks MLflow

OpenAPI

REST APIs

CI/CD

Observability

Security (multi-tenant)

Cost optimization

Tools

Databricks MLflow

AWS Bedrock

CloudFormation

AWS CDK

Docker

Job description

TetraScience is hiring a Senior Software Platform Engineer to shape the AI cloud for biopharma. You will design, build, and operate critical services and APIs enabling external researchers to run models on their own data at scale, with strong emphasis on cost, latency, and security.

You will own major parts of the AI platform end-to-end, collaborating with Applied AI and data engineering teams to deploy production-grade workflows, improve observability, and drive platform direction through