Staff Backend Engineer

Tekion is looking for talented Software Engineers who want to be part of building next-gen AI-native business applications in the cloud. You will use your passion and expertise to create world-class AI platform products. You should excel in working with large-scale applications and frameworks and have outstanding communication and leadership skills.

Responsibilities:

• Lead the technical vision and architecture for Tekion's AI Native Platform, the foundational layer powering AI capabilities across all Tekion products.
• Architect and build Tekion's AI gateway, a highly available, multi-provider LLM abstraction layer. Lead the design of Tekion's MCP (Model Context Protocol) ecosystem.
• Design and implement agentic AI frameworks.
• Drive AI platform reliability and observability.
• Provide technical mentorship and set engineering standards for the AI Native Platform team.
• Take end-to-end ownership of platform architecture decisions and be responsible for their success in production.
• Collaborate with product, AI/ML research, and domain engineering teams to define the AI platform roadmap.
• Deliver with quality, on time, in a fast-paced start-up environment.

Requirements:

• Bachelor's/Master's in computer science or relevant fields.
• 8+ years of relevant software engineering experience.
• Strong sense of ownership and technical leadership.
• Excellent Java and object-oriented development skills.
• Deep experience in building and scaling microservices.
• Strong problem-solving skills, technical troubleshooting, and diagnosis.
• Expected to be a role model for engineers, enforce high code quality, and drive engineering excellence within the team.
• Experience in developing backends for enterprise systems (e-commerce/manufacturing/supply chain, etc. ).
• Excellent understanding of debugging, performance, and optimization techniques.
• Experience with Java, MongoDB, MySQL, AWS technologies, the ELK stack, Spring Boot, and Kafka.
• Deep experience in cloud technologies and large-scale distributed systems.
• Deep expertise in LLM systems model selection and evaluation, token economics at scale, and context window optimization.
• Strong knowledge of MCP (Model Context Protocol) and tool-use standards, designing MCP ecosystems, tool schema governance, auth and trust models for MCP servers, and integration with multi-agent frameworks.
• Experience designing AI gateways / LLM infrastructure.
• Experience with agentic AI architectures, multi-agent systems, planning/reasoning frameworks (ReAct, Plan-and-Execute), tool orchestration, guardrails and safety layers, human-in-the-loop escalation, and agent evaluation.
• Proficiency in LLM observability and MLOps.
• Experience with AI safety, governance, and responsible AI patterns.
• Demonstrated ability to deliver in a fast-paced environment.
• Excellent communication and leadership skills.