Staff AI Engineer
About the role
- About Our Client:
The organization operates in the observability platform space, providing a fully managed solution used by over 10,000 organizations to enhance system reliability, accelerate incident resolution, and optimize telemetry at scale. Built on open source and open standards, the platform supports interoperability across diverse technology stacks and integrates AI capabilities to deliver unified data visibility. The organization serves major customers including Anthropic, Bloomberg, NVIDIA, Microsoft, and Salesforce, and supports a fully remote workforce distributed across more than 40 countries.
- About the Opportunity:
The Staff Engineer (AI & Automation) is responsible for leading the development and technical direction of AI agent infrastructure and automation systems that support the Marketing Operations organization. This role focuses on designing and delivering scalable AI-driven solutions to automate workflows across multiple teams, improving operational efficiency and enabling self-service capabilities. It involves building production-grade multi-agent AI architectures and backend services that connect AI models to various data platforms and business systems.
- Responsibilities:
Develop and maintain multi-agent AI systems from design through deployment and operation
Create modular agentic components using orchestration frameworks that function continuously across teams
Build reusable AI agent skills accessible via multiple interfaces such as Slack and internal applications
Implement observability features including logging, performance tracking, prompt refinement, and cost monitoring
Establish governance standards covering access control, audit trails, PII handling, and human oversight
Develop backend services including APIs and microservices integrating AI models with business platforms like BigQuery and CRMs
Architect data flows for retrieval-augmented generation connecting language models to knowledge bases and real-time data
Deploy scalable serverless or containerized services within cloud infrastructure
Collaborate with operational teams to identify automation opportunities and develop measurable solutions
Design workflows using orchestration tools with attention to CI/CD, testing, and production stability
Create documentation and enablement materials to support partner teams in operating systems independently
- Requirements:
Minimum 8 years in software engineering with backend development, systems integration, or data engineering experience
At least 2 years applying large language models and AI in production settings
Proficient in Python and JavaScript/Node.js, with experience in Git workflows and testing
Knowledge of LLM frameworks, prompt engineering, retrieval-augmented generation, and evaluation methods
Experience building and operating multi-agent AI systems including orchestration and state management
Ability to analyze business problems and design outcome-focused workflows
Familiarity with Google Cloud Platform services such as BigQuery, Cloud Functions, and Cloud Run
Understanding of LLM failure modes and mitigation strategies including human escalation and cost management
Skilled in AI-assisted development tools
Effective communicator capable of explaining complex technical concepts to diverse audiences
- Pay Range and Compensation Package:
The pay range and compensation package for this role will be determined based on the candidate’s experience, skills, and other relevant factors.
Equal Opportunity Statement: Our client is an equal opportunity employer. They celebrate diversity and are committed to creating an inclusive environment for all employees. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, or national origin.
Note:
RemoteHunter is a recruitment partner of this role. Please note that all employment decisions, including candidate assessment, interviews, hiring, compensation, and employment terms, are made exclusively by the hiring employer.
Responsibilities
- Develop and maintain multi-agent AI systems from design through deployment and operation
- Create modular agentic components using orchestration frameworks that function continuously across teams
- Build reusable AI agent skills accessible via multiple interfaces such as Slack and internal applications
- Implement observability features including logging, performance tracking, prompt refinement, and cost monitoring
- Establish governance standards covering access control, audit trails, PII handling, and human oversight
- Develop backend services including APIs and microservices integrating AI models with business platforms like BigQuery and CRMs
- Architect data flows for retrieval-augmented generation connecting language models to knowledge bases and real-time data
- Deploy scalable serverless or containerized services within cloud infrastructure
Qualifications
- Minimum 8 years in software engineering with backend development, systems integration, or data engineering experience
- At least 2 years applying large language models and AI in production settings
- Proficient in Python and JavaScript/Node.js, with experience in Git workflows and testing
- Knowledge of LLM frameworks, prompt engineering, retrieval-augmented generation, and evaluation methods
- Experience building and operating multi-agent AI systems including orchestration and state management
- Ability to analyze business problems and design outcome-focused workflows
- Familiarity with Google Cloud Platform services such as BigQuery, Cloud Functions, and Cloud Run
- Understanding of LLM failure modes and mitigation strategies including human escalation and cost management
Skills mentioned
About RemoteHunter
RemoteHunter is your dedicated AI job search assistant, turning the job hunt from a slow, individual effort into a quicker, smarter, and guided experience by streamlining each step of the process and speeding up your path to the right career opportunities.