Lead Software Platform Engineer, MLOps
New
T
TetraScienceScientific AI
United StatesFull-TimeLead
Salary200,000 - 270,000 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- 10+ years of professional experience in software engineering and infrastructure engineering
- Required Skills
- AWSDockerPythonTypeScriptRESTful APIsMLOpsDistributed Systems
Requirements
- 10+ years of professional experience in software engineering and infrastructure engineering.
- Track record designing, building, and scaling distributed, cloud-native systems in production.
- Experience as a technical leader or architect accountable for system design, scalability, performance, and cost decisions.
- Experience designing security for multi-tenant platforms, including tenant authorization boundaries and handling PII and PHI.
- Production experience building and maintaining AI/ML infrastructure as a multi-tenant product with external users.
- Hands-on experience taking LLM systems to production, including RAG architecture, retrieval and embedding design, prompt and model versioning, and tool or function calling.
- Expert-level TypeScript and Python skills for building APIs and backend services.
- Production-level experience with a model registry and serving stack; Databricks MLflow is preferred.
- Experience using AI evaluation as a release gate, including eval harnesses, regression gates, and drift or quality monitoring.
- Proficiency in API-first design, REST, and OpenAPI specifications.
- Working knowledge of AWS and containerized workloads such as Docker; familiarity with CloudFormation or CDK and CI/CD pipelines.
- Experience defining observability and SLI/SLO/SLA practices, including monitoring, alerting, and distributed tracing.
- Ability to explain technical ideas to customers and cross-functional teams, influence technical direction, and mentor engineers.
Responsibilities
- Own the technical architecture of the customer-facing AI/ML platform and its service and API surface.
- Manage the model and prompt lifecycle across Databricks MLflow and AWS Bedrock, including registration, versioning, promotion, rollback, and multi-model serving.
- Design inference infrastructure for real-time and batch workloads, including routing, batching, caching, concurrency, capacity planning, and graceful degradation.
- Integrate models and LLMs into production using RAG architectures and build the agentic layer, including tool calling, MCP tooling, and agent runtimes.
- Design platform-level security controls, including tenant boundaries, prompt-injection and tool-abuse defenses, and PII and PHI handling.
- Build AI evaluation and quality infrastructure, including eval harnesses, golden datasets, CI regression gates, A/B and shadow deployment, and production drift and hallucination detection.
- Establish monitoring, alerting, logging, and distributed tracing, and define SLI, SLO, and SLA practices.
- Design reproducibility, lineage, and audit trails for validated environments.
- Contribute to infrastructure-as-code and deployment automation using CloudFormation and AWS CDK.
- Own production readiness with Applied AI, data engineering, and platform teams, including performance, reliability, cost efficiency, incident response, and runbooks.
- Lead design reviews, produce reference architectures and technical documentation, mentor engineers, and set technical direction for AI infrastructure.
View Full Description & ApplyYou'll be redirected to the employer's site
