Senior AI Engineer (Conversational AI)

RemoFirst is a company focused on transforming the way businesses hire and manage global teams through an all-in-one global HR platform that simplifies hiring, compliance, payroll, and benefits management. The company has a team of 250+ people and serves market-leading customers like Microsoft and Mastercard.

• 5+ years of experience building AI-powered applications in production.
• Strong knowledge of Large Language Models (LLMs), prompt engineering, AI agents, RAG, tool calling, structured outputs, and orchestration frameworks.
• Proven experience designing and developing conversational AI systems (voice and/or chat applications).
• Strong understanding of AI system design, including context management, memory, retrieval, multi-agent workflows, and reasoning pipelines.
• Experience building AI evaluation frameworks, automated testing pipelines, benchmarking, and regression testing.
• Demonstrated experience improving AI quality through iterative evaluation and experimentation.
• Strong software engineering fundamentals, including clean architecture, design patterns, testing, and maintainable code.
• Experience integrating multiple AI providers such as OpenAI, Anthropic, Gemini, or similar.
• Experience deploying, monitoring, and maintaining AI applications in production environments.
• Full-stack development experience with modern backend and frontend technologies.
• Experience with cloud platforms, APIs, CI/CD pipelines, and production deployments.
• Strong analytical and problem-solving skills.
• Ability to evaluate multiple AI approaches and select the most effective solution based on quality, reliability, latency, and cost.
• Ability to independently own complex AI projects from design through production 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.

• Design, develop, and maintain production-grade conversational AI systems.
• Own AI features from technical design through deployment and production support.
• Design scalable AI architectures and agent workflows.
• Build and maintain AI evaluation frameworks, benchmarks, and automated testing pipelines.
• Continuously improve AI quality through experimentation, evaluation, and data-driven optimization.
• Integrate multiple AI providers and select the best models for different use cases.
• Monitor production AI systems and proactively improve reliability, quality, and performance.
• Collaborate with product, frontend, and backend teams to deliver end-to-end AI features.
• Review technical designs and contribute to engineering best practices.
• Troubleshoot complex AI and production issues while ensuring high-quality, maintainable solutions.
• Stay up to date with the latest advancements in Generative AI and apply them where they create business value.