Lead Software Platform Engineer, MLOps

Role: Lead Software Platform Engineer (MLOps)

You will lead the architecture and scaling of TetraScience’s AI and data infrastructure as a multi-tenant platform product used by customers to run production-grade AI/ML workflows.

What you will do

• Own the technical architecture of the AI/ML platform, including the service and API surface for models and agents running on customers’ scientific data.
• Own the model & prompt lifecycle across Databricks MLflow and AWS Bedrock, covering:
  • registration, versioning
  • asset bundles
  • staged promotion, rollback
  • multi-model serving
• Design inference substrate for real-time and batch workloads:
  • routing, batching, caching
  • concurrency control
  • GPU/accelerator capacity planning
  • large binary inputs (e.g., instrument images)
  • graceful degradation under load
• Integrate models and LLMs into production systems, including:
  • Retrieval-Augmented Generation (RAG)
  • agentic layers such as tool/function calling, MCP-based tooling, and agent runtimes
  • platform vs application responsibility boundaries
• Implement security by design and collaborate with security on:
  • prompt-injection and tool-abuse defenses
  • PII/PHI handling
  • strong multi-tenant data boundaries across prompts, retrieval, and tool calls
• Build evaluation and quality infrastructure to make AI shippable, including offline and online evaluation (continues beyond the provided text).

Requirements / fit

• Experience shipping AI/ML infrastructure as a multi-tenant product (not just internal tooling).
• Ability to turn scalability and cost targets into concrete technical strategy.
• Comfort operating in a regulated environment (customer compliance obligations; scientists in large pharmaceutical organizations).