Senior Software Engineer / Platform Architect

We are seeking a Senior Software Engineer / Platform Architect to design and lead an enterprise-grade agent-based AI platform and deliver AI-driven solutions for a healthcare client focused on Revenue Cycle Management (RCM) transformation. This is a senior technical leadership role for someone who has architected enterprise-grade, cloud-native, distributed systems and can bring strong rigor to LLM/agent orchestration, reliability, and developer productivity.

You will build the "agent platform foundation" (multi-LLM support, tool orchestration, evaluation, governance, and deployment patterns) that enables multiple RCM automation products and use cases to ship safely at scale.

Key Responsibilities

• Architect and build an agent-based AI platform supporting multiple LLM providers, RAG, prompt/tool orchestration, and portable agent packaging/SDK patterns.
• Define end-to-end architecture across data ingestion, retrieval, orchestration, evaluation, deployment, scalability, monitoring, and governance.
• Lead development of GenAI capabilities for RCM (e.g., intelligent document processing, financial summarization, decision support), with strong emphasis on verification, safety, and repeatability.
• Establish quality gates for agent-assisted development: evaluation harnesses, test automation, regression suites, and production guardrails.
• Drive production readiness: observability (metrics/logs/traces), reliability patterns, incident triage, and operational runbooks.
• Optimize cloud cost and performance (autoscaling, instrumentation, workload profiling, right-sizing) while maintaining SLA/SLO targets.
• Collaborate with business stakeholders, product owners, and engineering teams to translate RCM needs into scalable, secure platform capabilities and deliverables.
• Evaluate and integrate AI platforms, model providers, cloud services, and third-party tools into the healthcare ecosystem.
• Ensure solutions meet HIPAA, data privacy, and security requirements (PHI, access control, auditability, retention).
• Provide technical leadership: architecture reviews, mentoring, and setting engineering standards across teams including remote/async collaboration.

Required Skills & Qualifications

Technical Skills

• Deep expertise in software architecture for distributed, cloud-native systems (microservices, event-driven patterns, APIs, scalability).
• Strong experience with Python (required) and at least one additional systems language (e.g., Go/Java/C++) for performance-sensitive services.
• Hands-on experience with LLMs and agent/GenAI patterns: orchestration, tool calling, RAG, prompt management, and/or fine-tuning.
• Strong background in production engineering: monitoring/alerting, incident response, performance tuning, and reliability practices.
• Experience building developer tooling and delivery standards: CI/CD pipelines, linting/static analysis, testing strategy, release/versioning workflows.
• Knowledge of cloud platforms (AWS, Azure, or Google Cloud Platform) and AI services; experience deploying secure systems in regulated environments.

Domain / Regulated Environment Experience

• Experience delivering systems in regulated environments (healthcare, finance, government/DoD), including security and compliance controls.
• Healthcare RCM experience (claims, billing, denials, payment posting) is strongly preferred but not required for exceptional platform candidates.
• Familiarity with healthcare data and integrations (claims data, HL7, EHR/EMR, payer systems) is a plus.

Nice-to-Haves / Differentiators

• Open-source contributions, maintainer/committer experience, or experience working with OSS communities.
• Experience building agent platforms with modular "cognitive architecture" concepts, plugin tool ecosystems, or MCP-style client/server integrations.
• Evidence of driving measurable outcomes: cost reduction, throughput gains, latency improvements, reliability/SLO improvements.

What Success Looks Like

• A production-ready agent platform foundation is live: multi-LLM support, RAG, orchestration, evaluation, and governance.
• Teams can ship RCM automations faster with lower risk due to standardized SDKs, templates, CI quality gates, and observability.
• Measurable improvements in cost/performance/reliability (e.g., lower cloud spend per transaction, improved throughput, fewer incidents).