Senior AI Platform Engineer - Scalable ML Infra for Pharma

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

Benefits offered by this job

Stock options

100% employer-paid benefits

401(k)

Unlimited PTO

Flexible working arrangements

Life Insurance

Job summary

TetraScience is seeking a Senior Software Platform Engineer to build and operate AI and data infrastructure for biopharma customers. You will own major parts of the platform end-to-end, from design through production, collaborating with Applied AI and data teams to deliver cloud services and MLOps capabilities.

You will ship model serving, MCP, and agent capabilities used by scientists at large pharmas, ensuring scalability, cost control, and regulatory compliance in a regulated environment.

Qualifications

• 7+ years of professional experience in software engineering and infrastructure engineering.
• Experience taking technical ownership of a significant service or component, including design decisions on scalability, performance, and cost.
• Hands-on experience building and maintaining AI/ML infrastructure in production, including model deployment and lifecycle management.
• Hands-on experience taking LLM-based systems to production, including RAG architecture, retrieval and embedding design, prompt and model versioning, and tool or function calling.
• Experience building security into a multi-tenant platform, including authorization boundaries between tenants and handling of data such as PII and PHI.
• Strong coding skills in TypeScript and Python for building reliable APIs and backend services.
• Production experience with a model registry and serving stack (Databricks MLflow).
• Experience designing APIs with REST and OpenAPI that are scalable, secure, versioned, and extensible.
• Working knowledge of AWS and containerized workloads (Docker) and infrastructure-as-code (CloudFormation/CDK).
• Observability and SLI/SLO practice for production systems.

Responsibilities

• Design, build, and operate services and APIs for models and agents against customers’ data.
• Own the model and prompt lifecycle across Databricks MLflow and AWS Bedrock.
• Build inference paths for real-time and batch AI workloads with efficient routing and caching.
• Integrate LLMs into production systems using retrieval-augmented generation (RAG).
• Implement security guardrails, data boundaries, and PT/PHI handling.
• Develop evaluation tooling: offline/online eval, drift and quality monitoring.
• Set up monitoring, logging, and tracing with meaningful SLIs/SLOs.
• Ensure reproducibility and lineage with versioned data, code, prompts, and artifacts.
• Write IaC and deployment automation (CloudFormation, CDK) for multi-tenant infra.

Skills

Distributed systems

MLOps

Rest APIs

Security

Communication

Observability

Tools

TypeScript

Python

AWS

CloudFormation

CDK

Databricks MLflow

OpenAPI

Docker

Kubernetes

Job description

TetraScience is seeking a Senior Software Platform Engineer to build and operate AI and data infrastructure for biopharma customers. You will own major parts of the platform end-to-end, from design through production, collaborating with Applied AI and data teams to deliver cloud services and MLOps capabilities.

You will ship model serving, MCP, and agent capabilities used by scientists at large pharmas, ensuring scalability, cost control, and regulatory compliance in a regulated environment.