HubSync is an end-to-end platform for tax and audit firms. We handle document management, workflow automation, and AI-powered document processing for CPA firms during their busiest periods.  

We are transforming HubSync into an AI-native platform with agentic AI capabilities across all our key modules. We are looking for an experienced backend engineer who has built and shipped production systems that real users depend on.  

What We Are Building 

Active areas of work where you will have direct ownership: 

• Agentic workflow orchestration. Multi-agent coordination across tax document workflows with human-in-the-loop oversight. Agent state machines, tool routing, context windowing, and retry semantics for processes that run for minutes or hours. 

• Document intelligence at scale. Production-grade pipelines that extract, classify, and validate tax forms and financial documents across dozens of formats and quality levels. 

• Workflow state management. State hydration for long-running agentic workflows, failure handling, checkpoint/resume, and recovery across distributed services. 

• Evaluation and observability. Task completion rates, accuracy attribution, cost tracking per action, regression detection. Attributing outcomes to specific agent reasoning steps when something goes wrong. 

• Cost-accuracy optimization. Optimizing cost, accuracy, and latency trade-offs across different document types, complexity levels, and client tiers during peak tax season volume. 

• Trust and reliability. Making non-deterministic agent output trustworthy for professionals who cannot accept errors. Supervision layers, validation rules, human review gates. 

What We Look For 

You have built and shipped production systems. You have taken features from design through implementation to production release, and you have kept them running. You understand concurrency, failure modes, data integrity, and why things break at scale and can architect solutions end-to-end. 

You can point to enterprise-grade features and products that you built and that users rely on today. You have dealt with the full lifecycle: requirements, implementation, testing, deployment, monitoring, and the production incidents that follow. 

You work across the stack when the problem requires it. The boundaries between backend, data, infrastructure, and product work are not rigid here. The best work happens when engineers move between them based on what the problem demands. 

Must Have 

• 4+ years building and shipping backend systems in production environments where uptime and correctness matter 

• A track record of delivering enterprise-grade features and products, from design through deployment and ongoing operations 

• Deep experience with relational databases: PostgreSQL or equivalent, schema design, query optimization, data modeling, migrations 

• Hands-on work with event-driven architectures: message queues, async processing, distributed job execution 

• Production experience with AWS (Lambda, SQS, S3, ECS) or equivalent cloud platforms 

• Comfort reading and writing both TypeScript and Python (or the ability and willingness to pick up a second language quickly) 

• Experience with the full software delivery lifecycle: design, implementation, testing, deployment, monitoring, and incident response 

Good to Have 

• Exposure to agentic systems, agent orchestration frameworks, or multi-agent workflow design 

• Familiarity with RAG architectures, vector databases, or document processing pipelines 

• Experience with multi-tenant SaaS architecture (schema isolation, tenant-scoped data, access control) 

• Background in document intelligence: OCR, structured extraction from PDFs, form understanding 

• Open-source contributions, technical writing, or other public evidence of engineering depth 

Technologies & Frameworks 

Languages & Runtimes 

• TypeScript  

• Python 3.12  

• React 18 with module federation for microfrontend architecture 

• Node.js 20 (Fastify and Express services) 

AI & Agent Infrastructure 

• AWS Bedrock, AgentCore (Claude, Titan embeddings, cross-encoder reranking) 

• LangGraph for agent orchestration and state machine management 

• LangChain for tool chaining and model integration 

• MCP (Model Context Protocol) for dynamic tool generation from OpenAPI specs