Senior Software Platform Engineer, MLOps

TetraScience

. Design, build, and operate services and APIs enabling customers to run models and agents against their scientific data .

Posted 11/11/2026full-timeUnited StatesSenior💰 $170,000 - $220,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and operating AI/ML infrastructure, including model lifecycle management, security controls, and observability practices. Proficient in integrating LLMs into production systems and ensuring production readiness across multi-tenant environments.

Highest-signal resume keywords

AI/ML Infrastructure ManagementLLM-Based Systems ProductionSecurity in Multi-Tenant PlatformsTypeScript and Python Coding SkillsAWS and CloudFormation Experience

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Model RegistrationVersioningAsset BundlesREST and OpenAPI APIsDistributed Cloud-Native SystemsAI Evaluation and Quality ToolingInfrastructure-as-CodeCI/CD PipelinesObservability PracticesMonitoring and Alerting

Soft Skills

Clear CommunicationMentoringInfluencing Technical Direction

Tools & Technologies

Databricks MLflowAWS BedrockDockerCloudFormationAWS CDK

Industry Keywords

Prompt InjectionTool AbusePII HandlingPHI HandlingMulti-Tenant Infrastructure

Tech Stack

Tools & technologies

AWSCloudDockerPythonTypeScript

About the role

Key responsibilities & impact

Design, build, and operate services and APIs enabling customers to run models and agents against their scientific data
Build services used internally by Applied AI and data engineering teams
Own the model and prompt lifecycle across Databricks MLflow and AWS Bedrock, including registration, versioning, asset bundles, staged promotion, rollback, and multi-model serving
Build inference paths for real-time and batch AI workloads, including routing, batching, caching, concurrency control, capacity planning, large binary inputs, and graceful degradation
Integrate LLMs into production systems using retrieval-augmented generation (RAG)
Build agent capabilities including tool and function calling, MCP-based tooling, and agent runtimes
Implement security controls including guardrails, prompt-injection and tool-abuse defenses, PII and PHI handling, and tenant data boundaries
Build AI evaluation and quality tooling, including offline and online evaluation harnesses, golden datasets, CI regression gates, A/B and shadow deployment, and production drift and hallucination detection
Set up monitoring, alerting, logging, and distributed tracing; define SLIs and SLOs for probabilistic systems
Build reproducibility and lineage through versioned data, code, prompts, and model artifacts with audit trails
Write infrastructure-as-code and deployment automation using CloudFormation and AWS CDK
Support multi-tenant infrastructure, online upgrades, and on-demand compute
Own production readiness with Applied AI engineers, data engineers, and platform teams, including performance, reliability, cost, incident response, and runbooks
Participate in design reviews and write design and technical documentation
Mentor mid-level engineers
Evaluate frameworks, serving runtimes, and model providers and make build-versus-buy recommendations

Requirements

What you’ll need

7+ years of professional experience in software engineering and infrastructure engineering
Track record of building and running distributed, cloud-native systems in production
Experience taking technical ownership of a significant service or component, including scalability, performance, and cost decisions
Hands-on experience building and maintaining AI/ML infrastructure in production for users outside the candidate’s own team
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 tenant authorization boundaries and handling PII and PHI
Awareness of LLM-specific risks such as prompt injection and tool abuse
Strong coding skills in TypeScript and Python
Production experience with a model registry and serving stack, ideally Databricks MLflow
Experience with model registration, versioning, asset bundles, and serving workflows
Experience treating AI evaluation as a release gate, including eval harnesses, regression gates, and drift or quality monitoring
Experience designing scalable, secure, versioned, and extensible REST and OpenAPI APIs
Working knowledge of AWS and containerized workloads such as Docker
Familiarity with infrastructure-as-code such as CloudFormation or AWS CDK
Ability to contribute to CI/CD pipelines and deployment automation
Experience with observability and SLI/SLO practices, including monitoring, alerting, and distributed tracing
Clear communication with customers and cross-functional teams
Ability to influence technical direction on teams the candidate does not manage
No visa sponsorship is available for this position

Benefits

Comp & perks

Competitive compensation
Stock options in a VC-backed Series C company
100% employer-paid benefits for all eligible employees and immediate family members
401(k)
Unlimited paid time off (PTO)
Flexible working arrangements
Company-paid Life Insurance, LTD/STD