AI Engineer

PromptCube; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Equity

Health insurance

Remote setup stipend

Learning stipend

Flexible hours

Job summary

Phantom is seeking an AI Engineer to design, develop, and deploy AI-powered tools, agents, and automation that span the entire organization. You will connect LLMs with internal systems, APIs, and enterprise tools to enable intelligent workflows and build reusable infrastructure for teams to tailor their own AI experiences.

You will own the underlying AI infrastructure, collaborate with stakeholders to identify AI opportunities, and ensure security, reliability, and cost efficiency while driving

Qualifications

• Proven experience building production AI applications and platforms.
• Hands-on with LLMs such as OpenAI, Anthropic Claude, or open-source models.
• Python/TypeScript with API integration and backend services.
• Experience building AI agents, workflow automation, or applications that leverage LLM orchestration frameworks.
• Familiarity with RAG, tool calling, structured outputs, prompt engineering, and modern AI application patterns.
• Experience integrating applications with enterprise tools, internal systems, and third-party APIs.
• Understanding of cloud infrastructure, deployment practices, monitoring, and production reliability.
• Strong product mindset with the ability to work independently and deliver measurable impact.

Responsibilities

• Design, develop and deploy AI-powered tools, agents and automation across the organization.
• Connect LLMs and AI applications with internal systems, APIs and enterprise tools to enable seamless workflows.
• Build and maintain the underlying infrastructure, services and integrations that support reliable AI applications across teams.
• Partner with stakeholders to identify AI opportunities and translate business needs into technical solutions.
• Develop reusable components, frameworks and tooling for AI workflows across teams.
• Implement access controls, monitoring, observability and safeguards for security and reliability.
• Monitor model performance, usage and costs and identify opportunities to improve efficiency and outcomes.
• Drive innovation by evaluating new models and frameworks and bringing new capabilities to the organization.

Skills

LLM integrations

Python

TypeScript

API integration

Cloud deployment

Tools

LangChain

Claude Agent SDK

LangGraph

Enterprise connectors

Job description

Role overview

Phantom's AI Engineer builds AI tools, agents and automation for the whole organization, connecting LLMs to internal systems and turning them into reusable infrastructure and tooling. Remote-US; salary and equity are described as competitive in the original posting.

Responsibilities

• Design, develop and deploy AI-powered tools, agents and automation that streamline workflows and solve real business problems across the organization
• Connect LLMs and AI applications with internal systems, APIs and enterprise tools to enable seamless, intelligent workflows
• Build and maintain the underlying infrastructure, services and integrations that support reliable AI applications across teams
• Partner with stakeholders to identify AI opportunities, translate business needs into technical solutions, and help teams use AI tools effectively
• Develop reusable components, frameworks and tooling that make it easier for teams to build, customize and maintain their own AI workflows
• Implement access controls, monitoring, observability and safeguards so AI applications stay secure, reliable and maintainable
• Monitor model performance, usage and costs, and find opportunities to improve efficiency, quality and business outcomes

Qualifications

• A strong software engineering background building and maintaining production applications, services or internal platforms
• Hands-on experience developing applications using LLMs such as OpenAI, Anthropic Claude or open source models
• Proficiency in Python, TypeScript or a similar language, with API integration and backend service experience
• Experience building AI agents, workflow automation or applications that use LLM orchestration frameworks
• Familiarity with retrieval augmented generation (RAG), tool calling, structured outputs, prompt engineering and modern AI application patterns
• Experience integrating applications with enterprise tools, internal systems and third-party APIs
• Understanding of cloud infrastructure, deployment practices, monitoring and production reliability
• A product mindset, the ability to work independently and take ownership, and a genuine interest in AI with a bias toward measurable impact

Application conditions

• Listed location is Remote-US; remote does not imply worldwide eligibility
• The work covers AI tools, agents and automation across the whole organization, not a single product line
• No specific salary figure is given, so none is claimed here

Preferred qualifications

• Experience building internal AI platforms or enterprise AI automation solutions
• Familiarity with AI coding tools, agent frameworks and orchestration platforms
• Experience with LangChain, LangGraph, Claude Agent SDK or similar frameworks, plus MCP and enterprise connectors

Compensation and benefits

• Competitive salary and equity; no specific figure is given in the original posting
• Comprehensive insurance with the base medical, dental and vision plan fully covered, plus flexible hours, a remote setup stipend and a learning and development stipend

What this role focuses on

• This is a platform role for the whole organization, not a single chatbot
• The core output is reusable tooling and infrastructure that lets other teams build their own AI workflows
• Security and reliability are part of the job, not an afterthought: access control and monitoring are listed as duties

Application preparation (editorial suggestions)

• Prepare real experience building production applications with LLMs: AI agents, workflow automation or orchestration-framework applications
• Prepare examples of independent ownership and cross-team collaboration: turning an ambiguous business problem into a practical technical solution
• Check the original posting for residency and work authorization: the location is Remote-US, and remote does not mean worldwide eligibility

Responsibilities

Build AI Solutions: Design, develop, and deploy AI powered tools, agents, and automation that streamline workflows and solve real business problems across the organization.

Develop AI Integrations: Connect LLMs and AI applications with internal systems, APIs, and enterprise tools to enable seamless, intelligent workflows.

Own AI Infrastructure: Build and maintain the underlying infrastructure, services, and integrations that support reliable AI applications across teams.

Enable AI Adoption: Partner with stakeholders to identify opportunities for AI, translate business needs into technical solutions, and empower teams to leverage AI tools effectively.

Build for Scale: Develop reusable components, frameworks, and tooling that make it easier for teams to build, customize, and maintain their own AI workflows.

Ensure Security & Reliability: Implement appropriate access controls, monitoring, observability, and operational safeguards to ensure AI solutions are secure, reliable, and maintainable.

Optimize AI Usage: Monitor model performance, usage, and costs while identifying opportunities to improve efficiency, quality, and business outcomes.

Drive Innovation: Stay current with emerging AI technologies, evaluate new models and frameworks, and identify practical opportunities to bring new capabilities into the organization.

Requirements

Strong software engineering background with experience building and maintaining production applications, services, or internal platforms.

Hands on experience developing applications using LLMs such as OpenAI, Anthropic Claude, or open source models.

Proficiency in Python, TypeScript, or similar programming languages, with experience integrating APIs and building backend services.

Experience building AI agents, workflow automation, or applications that leverage LLM orchestration frameworks.

Familiarity with retrieval augmented generation (RAG), tool calling, structured outputs, prompt engineering, and modern AI application patterns.

Experience integrating applications with enterprise tools, internal systems, and third party APIs.

Understanding of cloud infrastructure, deployment practices, monitoring, and production reliability.

Strong product mindset with the ability to translate ambiguous business problems into practical technical solutions.

Ability to work independently, take ownership of projects, and collaborate effectively with both technical and nontechnical stakeholders.

A genuine interest in AI and a bias toward experimentation, execution, and measurable impact.

Nice to Have

Experience building internal AI platforms or enterprise AI automation solutions.

Familiarity with AI coding tools, agent frameworks, and orchestration platforms.

Experience with technologies such as LangChain, LangGraph, Claude Agent SDK, or similar frameworks.

Experience with MCP, enterprise connectors, and AI tool integrations.

Familiarity with LLM observability, evaluation frameworks, cost optimization, and usage analytics.

Experience implementing security, governance, and access controls for enterprise AI applications.

Experience working in a fast growing technology company where speed, ownership, and adaptability are essential.

Benefits and additional information

Competitive salary and equity

Comprehensive insurance (medical/dental/vision): base plan 100% covered

Flexible hours and a long-standing, supportive remote environment

Unlimited vacation: Take time when you need it (and we really mean it!)

401(k) retirement plan

Wellness stipend

Weekly meal stipend

Learning & Development stipend

Remote / WFH set-up stipend