AI Backend Engineer (Agents & LLMs)

Overview

Sojo Industries is a fast-growing industrial automation company revolutionizing the food and beverage industry with advanced robotics, mobility, and modular packaging solutions. We operate state-of-the-art facilities in Pennsylvania, California, Texas, and Indiana, supporting a thriving business with Fortune 500 customers.

In March 2024, we launched Sojo Shield, our custom Dock-to-Dock, Blockchain-enabled track and trace platform. Version 1.0 provides real-time traceability and FDA-compliant reporting, integrating physical and virtual worlds to enhance efficiency and transparency in the supply chain.

We are aggressively expanding and seeking dedicated, innovative individuals to join our team. Our seasoned executives and operators from the food and beverage industry serve top-tier brands, distributors, and manufacturers.

Join us at the forefront of industrial automation and help scale our Sojo Shield team as we continue to grow and innovate.

Job Overview

We are looking for a AI Backend Engineer to lead the design and development of AI-powered backend systems for our platform. This is a hybrid role with in-person collaboration in our Israel office, and you'll play a key role in shaping the technical direction of our AI infrastructure.

Key Responsibilities

• Own the architecture, design, and delivery of LLM-backed backend services used in core Sojo Shield workflows.
• Lead the development and evolution of APIs that expose AI capabilities to internal and customer-facing systems.
• Drive the productization of prompt-based and agent-based workflows using modern LLM frameworks, setting best practices for the team.
• Design and implement robust evaluation, monitoring, and observability frameworks for AI systems in production.
• Architect the integration of AI services into existing backend systems, ensuring scalability and reliability.
• Partner closely with product, platform, and data teams to define technical strategy and ship AI features end-to-end.
• Mentor engineers and help raise the technical bar across the team, including code quality, system design, and AI engineering practices.
• Continuously improve system robustness through advanced AI engineering and agent harness design.
• Evaluate and introduce modern LLM tooling, driving pragmatic adoption for real production problems.

Required Skills and Qualifications

• 4+ years of experience in backend or platform engineering, including significant ownership of production systems.
• Deep, hands-on experience building and scaling production backend services in Python.
• Proven experience designing, architecting, and maintaining APIs (REST, async services) at scale.
• Substantial hands-on experience integrating LLMs into real, production systems, including prompt engineering, inference optimization, and agent-based workflows.
• Demonstrated ability to work with large, real-world datasets and complex operational systems.
• Strong technical leadership skills, including experience guiding architectural decisions and mentoring other engineers.
• Excellent problem-solving skills and a strong product-oriented mindset.

Preferred Skills

• Expert-level experience with FastAPI (or similar Python backend frameworks).
• Deep familiarity with agent orchestration frameworks such as LangChain, LangGraph, MCP.
• Strong grasp of modern AI engineering tooling and best practices, agentic-AI patterns, and agent harness principles.
• Experience designing and operating Multi-Agent reasoning workflows in production.
• Track record of operating AI systems at scale in production environments.
• Familiarity with supply chain, logistics, or industrial AI engineering.

What We Offer

• Competitive salary and benefits package.
• Opportunity to work in a dynamic and growing company.
• Flexible hybrid work environment.
• Opportunities for professional growth and advancement.