Build and deploy AI agents using large language models (LLMs)
Implement backend services and APIs to support agent workflows
Develop and refine prompts, tools, and context strategies for agent reliability
Configure and extend agent orchestration (state management, tool calling, memory)
Integrate third-party services and AI platforms (e.g., voice, speech-to-text, messaging)
Deploy and operate services in AWS, including monitoring and basic DevOps workflows
Work on real customer problems with incomplete requirements and iterate toward solutions
Collaborate closely with senior engineers to learn system design and production patterns

2–4+ years of professional software engineering experience
Strong backend engineering skills (Python and/or TypeScript)
Experience building APIs, services, or event-driven systems in production
Hands-on experience working in cloud environments (AWS preferred)
Familiarity with modern AI platforms and services, including LLM providers and voice/speech systems (e.g., ElevenLabs, OpenAI, Whisper, similar)
Experience integrating third-party APIs and external services into production systems
Comfort working across code, configuration, prompts, and infrastructure
Ability to operate in ambiguous problem spaces and iterate toward working solutions
Strong ownership mindset and bias toward shipping real systems

Forward Deployed Engineer

Key skills