Senior AI Engineer
We are an IT services company based in San Francisco, USA. We build and acquihire expert engineering and data science teams to help our clients meet their business needs and solve operational challenges.
About the role
We are looking for an experienced Senior AI Engineer to develop and scale an AI Agent platform that automates customer interactions across voice, SMS, and chat channels.
You will design, build, and maintain production AI systems that handle high volumes of real-time conversations, integrate with external services, and automate business workflows. The role requires strong software engineering expertise, hands-on experience with AI agents, and the ability to deliver reliable, scalable solutions.
This position requires working hours from 3:00 PM to 11:00 PM Kyiv time.
Key responsibilities
- Design, develop, and scale AI agent systems for real-time, multi-turn customer interactions.
- Build and maintain APIs, backend services, and infrastructure supporting AI-driven workflows across multiple communication channels.
- Integrate AI agents with external tools, APIs, and business systems.
- Optimize system performance, response accuracy, latency, and reliability.
- Implement monitoring, observability, and evaluation processes for production AI agents.
- Own the development lifecycle, including architecture, implementation, deployment, and maintenance.
- Collaborate with engineering, product, and AI/ML teams to deliver and improve AI-powered features.
Required qualifications
- Minimum 8 years of professional software engineering experience.
- Strong programming skills in Go, Python, or Elixir.
- At least 1 year of hands-on experience deploying and maintaining AI agents in production environments.
- Experience building AI agents that interact with external tools, APIs, and automated workflows.
- Proven experience designing and maintaining distributed, high-throughput systems.
- Strong knowledge of backend development, API design, and production infrastructure.
- Experience with system monitoring, performance optimization, and troubleshooting.
- Strong problem-solving skills and ability to work independently in a fast-paced environment.
- English: Upper-Intermediate (B2) or higher, with strong communication skills.
Preferred
- Experience designing and implementing LLM evaluations, including accuracy, safety, reliability, and cost monitoring.
- Knowledge of prompt engineering, context management, and guardrail strategies.
- Experience with agent frameworks such as LangGraph, CrewAI, or AutoGen.
- Understanding of agent orchestration, memory management, and multi-step workflows.
- Experience with LLM fine-tuning and data curation.