Leads the team this role joins
Heads the group this role sits in
In-house, owns the opening
From your own Gmail and LinkedIn.
About the role
This is a senior, full-time, fully remote role open to candidates worldwide, focused on building conversational AI systems that run in production. The engineer owns AI features from technical design through deployment and ongoing support, with a strong emphasis on quality, evaluation and reliability. The company is a global HR and payroll platform with more than 250 staff, and the role reports to a Lead AI Engineer.
What you’ll do
- Design, build and maintain production conversational AI systems.
- Own AI features from technical design through deployment and production support.
- Design scalable AI architectures and agent workflows.
- Build evaluation frameworks, benchmarks and automated test pipelines for AI.
- Raise AI quality through experiments, evaluation and data-driven tuning.
- Integrate several AI model providers and choose the best model for each use case.
- Monitor live AI systems and improve their reliability, quality and speed.
- Work with product, frontend and backend teams on end-to-end AI features.
- Review technical designs and champion engineering standards.
- Troubleshoot complex AI and production problems.
- Track generative AI advances and apply them where they create business value.
What they’re looking for
- 5+ years building AI-powered applications in production.
- Strong knowledge of LLMs, prompt engineering, AI agents, RAG, tool calling, structured outputs and orchestration frameworks.
- Proven experience designing conversational AI for voice and/or chat.
- Understanding of context management, memory, retrieval, multi-agent workflows and reasoning pipelines.
- Experience with evaluation frameworks, regression testing and benchmarking.
- A record of raising AI quality through iterative evaluation and experimentation.
- Solid software engineering fundamentals: clean architecture, design patterns and testing.
- Experience integrating providers such as OpenAI, Anthropic or Gemini.
- Experience deploying, monitoring and maintaining AI applications in production.
- Full-stack experience with modern backend and frontend technologies.
- Experience with cloud platforms, APIs, CI/CD and production deployments.
- Ability to weigh AI approaches on quality, reliability, latency and cost, and to own complex projects with minimal supervision.
Nice to have
- Experience building traditional ML applications.
- Experience with AI observability, tracing and monitoring.
- Experience mentoring engineers and driving engineering best practices.
What’s on offer
- Competitive compensation.
- 100% remote work.
- Startup environment with autonomy, direct impact on revenue and support, and visibility to leadership.
Skills
Questions about this role
Is this role remote?
Yes, it is fully remote and listed as open worldwide.
How many years of experience are needed?
The posting asks for 5 or more years building AI-powered applications in production.
What is the employment type?
Full-time.
What does the package include?
Competitive compensation, 100% remote work, and a startup environment with autonomy and leadership visibility.