Backend Engineer – AI Agent Orchestration

Location: Remote (US)

Type: Full-time

Role Overview

We’re looking for experienced Backend Engineers to help design and implement the core orchestration and integration layer powering our AI agent platform. This role is foundational to building secure, observable, and high-performance agent communication and execution backends that integrate seamlessly with external tools, internal systems, and cloud infrastructure.

Key Responsibilities

• Design and develop the agent orchestration backend, including session management, memory interfaces, and inter-agent communication protocols.
• Implement secure and scalable API gateways and integration adapters for systems like Jira, GitHub, ServiceNow, and Confluence.
• Build and maintain microservices for runtime orchestration, agent state handling, and event-driven workflows.
• Ensure low-latency, high-availability processing pipelines for production-grade AI agents.
• Embed observability into all services, enabling rich logging, tracing, and metrics for agent performance monitoring.
• Collaborate with AI engineers, platform architects, and product teams to define and evolve backend system architecture.

Required Qualifications

• 5+ years of hands-on experience in backend software engineering.
• Strong proficiency in Go, Python, or Java, with experience building distributed systems.
• Proven experience with microservices architecture, API development, and event-driven systems.
• Knowledge of API security models, including OAuth2, API key validation, JWT, and role-based access control.
• Experience with observability stacks: Prometheus, OpenTelemetry, Grafana, ELK/Splunk.
• Familiarity with message queues and event buses such as Kafka, NATS, or RabbitMQ.
• Experience building systems with high uptime and operational resilience.

Preferred Qualifications

• Exposure to agentic frameworks like LangGraph, Semantic Kernel, or LangChain.
• Understanding of vector databases (e.g., FAISS, Weaviate, Pinecone) and semantic search integration.
• Experience building AI/LLM-aware runtimes and integrating with retrieval-augmented generation (RAG) pipelines.
• Background in observability-first design with tracing, correlation IDs, and service mesh integrations.
• Experience with CI/CD, containerization, and cloud-native deployment using Kubernetes and Docker.