Fullstack Engineer with AI

Aloware is #1 AI-driven phone system for CRMs. A leading cloud-based contact center software that enables businesses to seamlessly integrate their customer communications across multiple channels, including voice, text, and email. Our platform empowers sales and support teams to enhance customer engagement, improve lead management, and drive revenue growth through intelligent automation and robust analytics.

We're pre-Series A (in this economy!), cash-flow positive, and will continue to be profitable as a mantra for our business.

About the Role

We are looking for an expert full-stack engineer with AI experience to architect and build our next-generation intelligence layer. You will be responsible for integrating cutting-edge Generative AI technologies directly into our contact center platform, leveraging Large Language Models (LLMs) from providers like OpenAI, Anthropic, and Google Gemini. Your code will power the “brain” of AloAi. You will design systems that allow our customers to deploy autonomous voice and text agents that understand context, query knowledge bases via RAG (Retrieval-Augmented Generation), and resolve customer issues naturally. You will bridge the gap between our core SaaS application and modern AI microservices. As part of the engineering team, you will work closely with our CTO, tech-leads, and product managers to define how businesses interact with their customers using state-of-the-art AI.

Main Responsibilities

This role empowers you to thrive in a creative, fast-paced engineering environment focused on delivering cutting-edge AI features. As an Aloware AI engineer, you’d be working under the leadership of our CTO/co-founder. Your path to promotion goes thru your work on solving complex LLM challenges, delivering net new autonomous functionality, and ensuring our agents are secure and accurate.

Coding and Development:

• Design and implement robust integrations with major AI providers (OpenAI, Anthropic, and Google Gemini) to power conversational agents.
• Build Retrieval-Augmented Generation (RAG) workflows using OpenSearch or Elasticsearch to enable agents to answer questions based on specific customer data with high accuracy.
• Develop low-latency logic for Voice Agents (IVAs) by chaining Speech-to-Text, LLM processing, and Text-to-Speech APIs to handle live phone calls.
• Write clean, efficient, testable, and maintainable code. Our core tech stack is PHP, but we are open to Python or Node.js for AI services.

Quality Assurance:

• Design system prompts and security guardrails to ensure agents remain on-topic, professional, and secure during interactions.
• Implement automated evaluation pipelines to test prompts against edge cases before deployment to production.
• Ensure each piece of code, including prompts and model configurations, is thoroughly tested to maintain high standards.

Peer Interaction and Code Review:

• Actively participate in peer code reviews to enhance code quality and learn the intricacies of the core telephony platform.
• Provide support and assistance to other team members, specifically on interacting with the AI microservices.
• Help others with questions, issues, and challenges to promote a team-oriented environment.

Documentation:

• Write and maintain technical documentation for API specs and Prompt Libraries.
• Inform about new or updated dependencies, create deployment manuals, and produce instructional videos for new AI capabilities.

Path to Promotion - Innovation and Problem-Solving:

• Encourage generating creative ideas and innovative approaches to prompt engineering, token usage, and cost optimization.
• Show leadership in tackling complex challenges (e.g., reducing latency in voice bots) and contributing unique solutions.
• Demonstrate an ability to think outside the box, leading to improvements in processes or products.
• Act as a mentor or guide for less experienced team members, fostering a culture of learning and growth.

Requirements

• 5+ years experience as a software engineer working on a VueJS/PHP/MySQL/AWS stack. We are open to Node.js and Python for AI services, but our core application is written in PHP/Laravel and VueJS.
• Generative AI Experience: Proven experience building applications using APIs from OpenAI, Anthropic, or Google Gemini. You understand embeddings, tokens, and context window management.
• Vector Search: Experience implementing RAG using OpenSearch, Elasticsearch, or vector databases.
• API Integration: 2+ years experience designing and consuming REST APIs. You know how to handle asynchronous tasks and long-running requests associated with LLM processing.
• Full Stack Awareness: Demonstrated experience working with VueJS or React is a must-have for this position. All our software engineers touch our UI at one point or another to visualize their features.
• Experience working in the API layer with security, logging, throttling, and modifying requests and responses.
• Background related to telecommunications, VOIP, digital messaging, chatbots, or CRM software is a strong plus.

As part of this position, you are an engineer on-call on a rotational basis every two weeks following deployments. While emergencies don’t happen often, we do require an engineer on-call to maintain our quality of service.


With a global team spanning 15+ countries we value and celebrate diversity where every individual feels empowered to contribute their unique talents, ideas, and experiences, driving our global success

**Role open and available for Latam and Europe remote ONLY**