What are the responsibilities and job description for the Senior Software Engineer, Backend (AI Agents) position at Loman AI?
About Loman AI
Loman AI is revolutionizing restaurant operations with the industry’s leading Voice AI solution. We handle every inbound call - from orders and reservations to customer questions - ensuring restaurants never miss an opportunity. Our AI agent works 24/7, delivering consistent, exceptional service that helps restaurants grow their business while reducing operational burden.
We’re a seed-stage startup experiencing rapid growth, and we’re building the team that will help us capture significant market demand.
The Role
We're seeking a Backend Engineer with specialization in Agentic Systems to own and evolve the core intelligence of our voice agents. This is a foundational role where you'll architect the conversational flows, optimize performance, and introduce cutting-edge AI capabilities that directly impact thousands of restaurant interactions daily.
This role demands equal excellence in prompt engineering and software development (50/50 split). We need someone with strong engineering fundamentals who can build robust, scalable systems - not just experiment with prompts. You'll be writing production code that handles millions of conversations.
What You'll Do
- Design and optimize complex agentic workflows - Build sophisticated multi-step conversational flows with dynamic function calling, state management, and context handling
- Drive prompt engineering excellence - Develop, test, and iterate on prompts that handle the nuanced complexity of restaurant operations
- Build evaluation frameworks - Create comprehensive testing suites to measure and improve agent performance across diverse scenarios
- Implement cutting-edge features - Own the development of advanced capabilities including conversation memory, personalization, and context-aware responses
- Write production-grade code - Develop scalable backend services, APIs, and infrastructure to support our AI agents
- Stay ahead of the curve - Research and implement the latest LLM techniques, tools, and best practices to maintain our competitive edge
- Collaborate cross-functionally - Work directly with the engineering team to integrate AI capabilities seamlessly into our product
What We're Looking ForRequired
- Proven experience with complex agentic systems - You've built production AI agents with multiple tools, functions, and sophisticated state management
- Deep prompt engineering expertise - Mastery of advanced techniques like few-shot learning, chain-of-thought reasoning, and prompt optimization
- Strong TypeScript/Node.js proficiency - Ability to implement robust, scalable solutions beyond just prompts
- Up-to-date AI knowledge - Active engagement with the latest LLM research, tools, and industry developments
- Systems thinking - Experience with evaluation frameworks, A/B testing, and data-driven optimization
- Startup mindset - Thrives in ambiguity, moves fast, takes ownership, and is energized by rapid iteration
Preferred
- Experience with voice AI or conversational systems
- Familiarity with observability tools like Langfuse
- Background in restaurant tech or high-volume customer service applications
- Experience with multiple LLM providers and model selection
Benefits
- Competitive market salary and meaningful equity stake
- Health insurance, including vision and dental
- Unlimited PTO/Sick leave
- Hybrid office policy (3-4 days in our Austin office)
- Own the most exciting and dynamic part of our tech stack
We do not sponsor visas or provide relocation assistance.
Important Note
This is a startup environment where we move fast and prioritize results. We’re looking for someone who thrives in ambiguity, takes ownership, and is energized by the pace of early-stage company building. High availability and strong work ethic are essential - this role is perfect for those who want to make a significant impact and grow with a rapidly scaling company.
