Eloquent AI
AI Engineer, Agent
About this role
Eloquent AI is seeking an AI Agent Engineer to build and deploy autonomous AI systems that handle complex workflows for enterprise clients in finance and insurance. You'll develop conversational agents, fine-tune language models, and integrate AI solutions with enterprise systems while working closely with customers and cross-functional teams.
What you'll do
- Build, deploy, and optimize enterprise-grade AI agents for high-stakes conversations
- Train and fine-tune LLMs for improved accuracy and real-world performance
- Integrate AI agents with enterprise systems via APIs, databases, and automation tools
- Work directly with customers to assess needs and implement customized AI solutions
- Conduct rapid experimentation to enhance agent interactions and automation capabilities
- Monitor agent performance through user simulations and evaluations
What they're looking for
- Python and deep learning frameworks (PyTorch, TensorFlow)
- LLMs and NLP model development, including fine-tuning and optimization
- API design and cloud infrastructure (AWS, GCP, Azure)
- Prompt engineering and parameter-efficient fine-tuning (PEFT)
- Retrieval-augmented generation (RAG) and agent development
- Software development and enterprise system integration
- Problem-solving and rapid prototyping
- Customer collaboration and requirements analysis
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Eloquent AI
Eloquent AI builds autonomous AI agents and systems powered by large language models to handle complex enterprise workflows in financial services and insurance. The company is hiring front-end engineers, full-stack AI engineers, senior infrastructure engineers, and AI specialists to develop conversational interfaces, scalable backends, production deployment systems, and multimodal AI agents.
View all jobs at Eloquent AILikely interview questions
- Walk us through a production LLM or NLP project you built end-to-end. How did you approach fine-tuning, and what metrics did you use to evaluate performance?
- Tell us about a time you had to integrate an AI model with enterprise systems or APIs. What were the challenges, and how did you solve for latency or reliability?