AI Backend Engineer

Photon; Scottsdale (AZ); Sur place; USD 150 000 - 190 000; Plein temps

Résumé du poste

Photon is seeking a hands-on Senior/Lead Backend Engineer with strong experience in AI agents and agentic workflows to design and build scalable backend services. You will integrate LLMs, tool-calling, and AI workflows while collaborating with Product and Business stakeholders.

You will lead, mentor, and deliver across REST APIs, microservices, and event-driven architectures, working onsite in Arizona or Rhode Island.

Qualifications

• 7+ years of backend/software engineering experience in a Senior/Lead role.
• Hands-on development with Node.js/TypeScript and/or Python.
• Experience building AI agents and agentic workflows using LLMs.
• Strong knowledge of LLM tool calling, prompt design, and AI evaluation techniques.
• Experience developing and consuming REST APIs and event-driven architectures.
• Strong understanding of microservices and distributed backend systems.
• Ability to work onsite in Arizona, USA (or Rhode Island) and collaborate with Product/Business teams.

Responsabilités

• Design, develop, and maintain scalable backend services.
• Build and integrate AI agents, agentic workflows, and LLM-powered apps.
• Implement LLM tool/function calling and prompt engineering.
• Develop REST APIs, microservices, and event-driven services.
• Design reliable integrations across AI services and external systems.
• Partner with Product/Business teams to translate requirements into tech solutions.
• Provide technical leadership, code reviews, and architecture guidance.
• Lead and mentor an offshore engineering pod to ensure quality delivery.

Connaissances

Backend engineering

Node.js/TypeScript

Python

AI agents / agent workflows

LLM tool calling

Prompt engineering

REST APIs

Microservices

Offshore team leadership

Outils

OpenAI/LLM platforms

Azure OpenAI / AWS Bedrock

Kubernetes

CI/CD

Description du poste

We are seeking a hands-on Senior/Lead Backend Engineer with strong experience in AI agents and agentic workflows to design and build scalable backend services and AI-powered solutions. The ideal candidate will combine strong backend engineering skills with practical experience integrating LLMs, tool-calling, and AI agent workflows, while working closely with Product and Business stakeholders.

Key Responsibilities

• Design, develop, and maintain scalable backend services using Node.js/TypeScript and/or Python.
• Build and integrate AI agents, agentic workflows, and LLM-powered applications.
• Implement LLM tool/function calling, prompt engineering, evaluation frameworks, and AI workflow orchestration.
• Develop and integrate REST APIs, microservices, and event-driven services.
• Design reliable integrations across AI services, enterprise applications, databases, and external systems.
• Partner directly with Product and Business teams to translate requirements into technical solutions.
• Provide technical leadership, code reviews, architecture guidance, and hands-on development.
• Lead and mentor an offshore engineering pod, ensuring delivery quality and alignment with project objectives.
• Monitor, troubleshoot, and optimize backend and AI workloads for performance, scalability, and reliability.

Required Qualifications

• 7+ years of backend/software engineering experience, with experience in a Senior/Lead capacity.
• Strong hands-on development experience with Node.js/TypeScript and/or Python.
• Practical experience building AI agents and agentic workflows using LLMs.
• Strong understanding of LLM tool/function calling, prompt design, and AI evaluation techniques.
• Experience developing and consuming REST APIs and working with event-driven architectures/services.
• Strong understanding of microservices, distributed systems, and backend architecture.
• Excellent communication and stakeholder-management skills, with the ability to work directly with Product and Business teams.
• Experience leading or coordinating offshore engineering teams/pods.
• Ability to work onsite in Rhode Island or Arizona, USA.

Preferred Qualifications

• Experience with LLM/AI platforms such as OpenAI, Azure OpenAI, AWS Bedrock, or Google Vertex AI.
• Experience with RAG, vector databases, embeddings, and AI orchestration frameworks.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Familiarity with CI/CD, containers, Kubernetes, and observability tools.