Remotery

Senior Staff AI Platform Engineer

atSentinelOneRemoteUS flagUnited StatesFull-timePlatform EngineerSenior$184k – $253k/year

Posted Jul 17

This is a fully remote position, open to applicants in United States.

📋 Description

• Design, develop, and manage components of the AI Gateway, which includes centralized identity and authentication/authorization, token budgeting, DLP and content guardrails, multi-model routing and failover, MCP allow-listing, and request-level audit logging.

• Create and sustain elements of the Harness layer, including agent orchestration (LangGraph or a similar tool), prompt construction and context management, memory and state management across multi-turn interactions, and model abstraction among providers such as AWS Bedrock and Google Vertex.

• Build and enhance production services utilizing Python (FastAPI) and pydantic.ai for LLM-powered components, while also contributing to the React/TypeScript interfaces that showcase platform capabilities to internal teams.

• Implement MCP/tool wiring for both internal and SaaS-embedded agents, ensuring that all callers, regardless of origin, adhere to the same policy controls.

• Contribute to the Claude and Gemini Enterprise plugin framework by developing, testing, and securing role-based skills and agents, as well as assisting in refining the pipeline for plugin authorship, evaluation, and deployment.

• Equip the platform for observability by incorporating metrics, tracing, and audit trails, and engage in on-call and operational support for platform services.

• Produce clear technical documentation and actively participate in architecture and code reviews, maintaining high standards for quality, security, and maintainability.

• Collaborate with engineers from Enterprise Data, Enterprise Apps, Product Development, and Infosec to integrate the platform with governed data sources and mutual architectural contracts.

• Work alongside the Sr. Director and model evaluation tooling to facilitate the connection between evaluation results and decisions regarding model selection, prompt tuning, and routing.


⛳️ Requirements

• Practical experience in building production services that interface with multiple consumers such as API gateways, internal platforms, or data platforms, with real exposure to authentication/authorization, rate limiting, observability, or audit logging; direct experience with AI and LLM platforms is highly advantageous but not mandatory.

• Hands-on experience with agent orchestration frameworks (LangGraph or an equivalent) and interfacing with hosted model providers like AWS Bedrock or Google Vertex, coupled with a solid understanding of context windows, memory, and tool-calling in production environments beyond theoretical knowledge.

• A minimum of 8 years of professional software engineering experience, particularly in building or operating AI and ML infrastructure within a production setting.

• Proficient in Python, preferably with FastAPI, and willingness to learn frameworks such as pydantic.ai for LLM-powered components; familiarity with React and TypeScript is a bonus.

• Exposure to or interest in the Model Context Protocol (MCP) and the complexities associated with governing tool access for agents functioning across enterprise systems.

• Knowledge of enterprise AI deployments, such as Claude Enterprise (Anthropic) or Gemini Enterprise, including their administration and the operation of access and policy controls, is a plus.

• Strong software engineering principles including the production of clean, tested code, robust API design capabilities, and the ability to provide and receive constructive feedback during code and architecture reviews.

• Comfortable navigating a fast-paced, evolving platform environment that thrives on ambiguity, with a passion for transforming a rough architecture into dependable, operational infrastructure.


🏝️ Benefits

• Restricted Stock Units (RSUs)

• Employee Stock Purchase Plan (ESPP)

• Flexible time off

• Paid company holidays and paid sick time

• Gender-neutral parental leave

• Grandparent leave

• Medical, dental, and vision coverage

• 401(k) retirement plan with company match

• Life and disability insurance

• Health and dependent care FSA

• Voluntary benefits (hospital, accident, critical illness)

• Employee Assistance Program (EAP)

• ARAG pre-paid legal

• Nationwide pet insurance

• Cancer Care program

• Global business travel medical insurance

• Home office allowance

• Mobile phone reimbursement

• Wellness coach

• Wellness/gym reimbursement

• Fertility coverage

• Adoption & surrogacy reimbursement

People also viewed

Quantiphi16 hours ago

Platform Engineer

CA flagCanada, +1 more countryFull-timePlatform Engineer
ApplyView job
Encompass Corporation16 hours ago

Senior Platform Engineer

RS flagSerbia OnlyFull-timePlatform Engineer
ApplyView job
Shippit18 hours ago

Senior Platform Engineer

ID flagIndonesia OnlyFull-timePlatform Engineer
ApplyView job
Group O18 hours ago

Associate Power Platform Developer

US flagIllinois OnlyFull-timePlatform Engineer$65k – $75k/year
ApplyView job
ServiceTitan21 hours ago

Staff Software Engineer, Platform – DevEx

US flagCalifornia, +8 more statesFull-timePlatform Engineer$185.3k – $297.4k/year
ApplyView job
New Era Technology21 hours ago

Senior QRadar Platform Engineer

US flagUnited States OnlyFull-timePlatform Engineer$80 – $125/hour
ApplyView job

Never miss a great job!

Get handpicked remote jobs straight to your inbox weekly.

Trusted by 7,400+ designers