Senior Software Engineer - Agentic AI Platform

Overview

Build the core agent runtime, workflow orchestration and integration platform that powers JazzX AI's enterprise digital workers.

What you'll do

• Design and build production-grade backend services and reusable platform capabilities for agent runtime, orchestration, state, memory, guardrails and model access.
• Develop agentic workflows using planning, tool use, multi-agent collaboration, parallel execution, reflection and human-in-the-loop.
• Build durable, long-running workflows with retries, timeouts, state management, recovery and compensation.
• Design asynchronous and event-driven systems using queues, messaging and distributed processing.
• Build secure enterprise integrations, APIs and protocol-based interfaces for tool invocation and agent-to-agent communication.
• Build end-to-end observability, tracing and auditability across agent decisions, model calls, tools and workflows.
• Design for security, reliability, scalability and performance, including identity, authorization, data protection and AI-specific risks.
• Partner with product, security and engineering teams to translate complex business workflows into reliable AI solutions.
• Participate in architecture and code reviews, mentor engineers and influence technical direction and engineering standards.

What you'll need

• 7–10 years of software engineering experience building backend and distributed systems.
• Strong hands-on Java and/or Python development experience building production services and APIs.
• Practical experience building agentic AI applications, including LLM integration, tool/function calling and workflow orchestration.
• Strong understanding of distributed systems, asynchronous processing, event-driven architectures and state management.
• Experience with databases, APIs, containers, Kubernetes and cloud-native development.
• Strong engineering practices across testing, CI/CD, code reviews, production troubleshooting and operational excellence.
• Understanding of agent patterns including planning, memory, reflection, multi-agent workflows and human-in-the-loop.
• Understanding of AI risks including prompt injection, data privacy, access control and model evaluation.
• Strong ownership and problem-solving mindset, with the ability to navigate ambiguity and make pragmatic technical trade-offs.
• Excellent communication and collaboration skills, with the ability to influence across engineering, product, security and architecture teams.
• Demonstrated ability to mentor engineers, drive technical discussions and raise engineering standards.

Nice to have

• Experience with LangGraph, OpenAI SDK or similar agent frameworks/SDKs.
• Familiarity with MCP, A2A, AG-UI or A2UI.
• Experience with Temporal, RAG, vector databases, agent memory or enterprise knowledge systems.
• Experience with model gateways, routing, guardrails, cost controls or AI evaluation.
• Experience with Azure/AKS, PostgreSQL, Kafka, Redis or OpenTelemetry.
• Experience building secure, multi-tenant platforms or software for regulated industries such as lending or financial services.
• Experience operating AI/agentic workloads in production at scale.