Note: The job is a remote job and is open to candidates in USA. LaborRX is an AI-powered workforce intelligence platform focused on Skilled Nursing Facilities, seeking a Staff Engineer who can lead the evolution of their autonomous shift fill engine. The role involves owning the architecture, mentoring engineers, and driving the technical direction of the team while leveraging AI technologies.

Responsibilities

• Own and evolve the post-publication autonomous shift fill engine
• Design and implement new agentic workflows
• Build MCP-style tool layers, skill modules, and agent orchestration patterns using LLM APIs (OpenAI, Anthropic, or equivalent)
• Maintain strict separation between per-facility policy configuration and core agent logic — our agents are configurable, not opinionated
• Own the NestJS/TypeScript monolith architecture — identify where it needs to evolve (modularization, event-driven patterns, background job infrastructure)
• Build the analytical data layer
• Design schemas and query patterns that support both real-time operational queries and retrospective analytics
• Know when to reach for PostgreSQL, when to aggregate, when to cache — and implement accordingly
• Meaningful AWS experience: comfortable owning infra decisions across our four environments (Production, Staging, Development, Demo)
• CI/CD pipeline ownership — ensure deployments are fast, safe, and automated
• Container strategy (Docker), environment parity, and deployment reliability
• Set architectural standards, review design docs, and make the call on disputed technical decisions
• Conduct code reviews that teach, not just approve or reject
• Work directly with the product and CEO on translating business logic (HPPD rules, agency cost models, CMS compliance requirements) into correct, testable code
• Be the person the team comes to when the problem is hard

Skills

• 8+ years of software engineering experience, with at least 3 at Staff or Principal level (or equivalent scope/impact)
• Must have shipped AI agents or AI-powered automation into production — not a POC, not a demo, not a hackathon project. Show us the repo, the architecture doc, or the demo. We will ask
• Deep TypeScript/Node.js expertise — our backend is NestJS and we're not changing that
• Strong PostgreSQL knowledge: complex queries, indexing strategy, migration management, performance tuning
• Comfortable with LLM APIs: function calling, tool use, multi-step agentic workflows, prompt engineering for deterministic outputs
• AWS fluency: EC2/ECS/RDS at minimum; bonus for Lambda, SQS, CloudWatch, deployment pipelines
• Built agent systems using LangChain, LlamaIndex, custom orchestration, or direct LLM API tool use
• Written skills/tools/functions that agents can call to take real-world actions
• Used Cursor, Claude, or Copilot as a core part of your development workflow — not an occasional helper
• Can articulate the difference between an LLM chain and an agent loop, and when each is appropriate
• React / React Native experience — you don't need to be a frontend specialist but you shouldn't be afraid of it
• Experience in healthcare tech, HIT, or any regulated industry with complex domain logic
• Experience with real-time systems: websockets, event-driven architectures, push notification infrastructure
• Familiarity with payroll/HRIS integration patterns (Paycor, ADP, similar)
• Background in multi-tenant SaaS with per-tenant configuration systems
• CI/CD ownership using GitHub Actions, Bitbucket Pipelines, or similar

Company Overview