Job Description

We’re building an AI-powered digital workspace platform that combines conversational AI, modular web applications, and enterprise-grade backend orchestration into a single system.
The platform enables organizations to interact with intelligent agents that can reason, retrieve contextual knowledge, execute structured workflows, and integrate with external and internal OneReach systems. It goes far beyond a simple chatbot — it’s a production-grade AI platform designed for reliability, scalability, and real-world enterprise use.
Our stack blends modern full-stack development (TypeScript, Node.js, Vue, PostgreSQL), event-driven architecture, and cloud infrastructure with advanced AI capabilities such as Retrieval-Augmented Generation, multi-step agent orchestration, and AI evaluation frameworks.
You’ll work at the intersection of software engineering and applied AI — building systems that make intelligent agents reliable, observable, and scalable in production.

Requirements:

Must-have skills

• Strong proficiency in TypeScript

• Hands-on experience with NestJS for backend development

• Solid knowledge of TypeORM and PostgreSQL

• Experience working with SQS (or similar message queue systems)

• Practical experience with Vue.js (both Vue 2 and Vue 3)

• Strong understanding of REST API design principles and integration with external services

• Basic knowledge of Terraform

• Deep understanding of end-to-end (E2E) testing frameworks and best practices

• Practical experience designing and maintaining automated E2E test suites, including testing AI-powered and agent-based applications

• Experience developing and maintaining Retrieval-Augmented Generation (RAG) systems

• Strong understanding of agentic AI architectures and the ability to operate, evaluate, and improve AI agent capabilities in production environments

Nice-to-have

• Experience with AWS and serverless infrastructure

• Familiarity with frontend testing frameworks

• Knowledge of microservices architecture

• Experience evaluating LLM performance, prompt strategies, and agent orchestration patterns

• Familiarity with observability and evaluation tooling for AI systems (e.g., tracing, prompt/version tracking, automated evaluation pipelines)

Responsibilities:

• Design, develop, and maintain full-stack features across a distributed AI-powered platform, ensuring scalability, reliability, and long-term maintainability.

• Own backend services built with TypeScript and Node.js frameworks, including API design, data modeling, asynchronous processing, and integration with external systems.

• Build and evolve frontend applications using modern Vue.js patterns, ensuring clean architecture, performance optimization, and a high-quality user experience.

• Contribute to infrastructure-as-code workflows, collaborating on cloud provisioning, environment configuration, and deployment pipelines.

• Develop and maintain comprehensive automated test coverage, including unit, integration, and end-to-end testing, with a strong emphasis on validating complex AI-driven workflows and multi-step agent interactions.

• Design, implement, and optimize Retrieval-Augmented Generation pipelines, including document ingestion, embedding strategies, vector search, and evaluation of response quality.

• Work on production-grade AI agent architectures: orchestrating multi-step reasoning flows, integrating LLMs with external systems, managing tool usage logic, and ensuring predictable, controllable behavior.

• Continuously evaluate and improve AI performance by analyzing outputs, refining prompts, tuning orchestration logic, and implementing automated evaluation strategies.

• Collaborate closely with product, design, and leadership to translate ambiguous requirements into structured technical solutions.

• Participate in architectural discussions and contribute to evolving platform standards, coding conventions, and engineering best practices.

• Take ownership of production incidents when needed, proactively improving system reliability, performance, and developer experience.

• Mentor other engineers where appropriate and contribute to a culture of high technical standards, clarity of communication, and pragmatic decision-making.

Benefits:

• Join an award-winning and innovative product company

• Work with smart, passionate teammates who genuinely love what they do

• Get hands-on exposure to cutting-edge topics in UX, AI, and technology

• Flexible remote work environment

• 24 paid days off per year

Our hiring process:
1. Call with HR — up to 30 minutes
2. Profile/CV review by Engineering Manager
3. Tech Interview with live coding — up to 2 hours
4. Interview with Engineering Manager (optional)
5. Job offer

Why OneReach.ai?
At OneReach.ai, we’re building a better way for humans and machines to work together. Our platform enables teams to create AI-powered communication and automation solutions with minimal code, and you’ll play a key role in supporting those experiences. If you’re passionate about technology, customer success, and continuous learning, we want to hear from you.