Python with AI Engineer

We are seeking a talented and experienced AI and Python Engineer to design, develop, and deploy cutting-edge phone integration solutions for our Agentic AI platform within the health insurance sector. This pivotal role involves building intelligent, autonomous agents on an Interactive Voice Response (IVR) system to streamline member interactions, automate workflows (e.g., claims processing, benefits verification), and enhance the overall member experience. The ideal candidate will combine deep agentic AI expertise with strong software engineering skills, a solid understanding of healthcare data standards, and a proven track record of implementing robust AI safety and guardrail mechanisms.

Key Responsibilities

• Design and Development : Architect and build agentic AI systems and multi-agent workflows using Python and frameworks like LangChain, LangGraph, or AutoGen, specifically for voice / telephony interfaces on an IVR platform.
• AI Safety & Guardrail Implementation : Design, implement, and enforce technical safety mechanisms across the AI system lifecycle to prevent privacy breaches (e.g., PII / PHI leaks), mitigate hallucinations, and ensure responses align with corporate policies and brand values.
• Phone / IVR Integration : Develop robust phone integration capabilities, leveraging VoIP, RESTful APIs, and other relevant technologies to ensure seamless data flow between the IVR platform, enterprise systems (EHR / CRM), and the AI agents.
• LLM Integration & Prompt Engineering : Utilize and fine-tune Large Language Models (LLMs) for natural language processing (NLP) and develop structured prompts, function calling mechanisms, and memory systems to enable agents to reason, plan, and execute multi-step healthcare tasks autonomously.
• Healthcare Domain Expertise : Apply a deep understanding of healthcare workflows, data standards (e.g., HL7, FHIR), and regulatory requirements (e.g., HIPAA) to ensure all AI solutions are compliant, secure, and patient-centered.
• Testing and Evaluation : Implement comprehensive evaluation frameworks, including adversarial testing agents, offline / online LLM evaluations, and A / B testing, to measure agent performance (accuracy, hallucination rate, safety) and continuously improve system reliability and compliance.
• Deployment and MLOps : Deploy scalable AI solutions in cloud environments (AWS, Azure, GCP) using Docker and Kubernetes, and manage the AI development lifecycle with CI / CD pipelines, observability, and cost optimization.
• Collaboration : Work closely with cross-functional teams, including product managers, data scientists, software engineers, and legal / compliance teams, to translate business requirements into safe and compliant technical solutions.

Required Skills and Qualifications