Full-Stack AI Software Engineer (Python / React)

We are seeking experienced Full-Stack AI Software Engineers (Python / React) to join an innovative project building a conversational Voice AI platform for the US HealthTech market. The core objective of the system is to conduct natural, real-time conversations, maintain long-term contextual memory, and analyze conversational data to detect early signals of emotional or cognitive decline in patients.
Details
•

Role: Full-Stack AI Software Engineer (Python / React)
• Seniority: Mid / Senior (4+ years of software engineering experience with strong exposure to AI)
• Engagement Model: B2B Contract, Full-time
• Work Model: Remote (Poland-based with flexible overlap for US working hours)
• Client Location: US-based
• Language: Fluent English (C1 – working language for direct client communication)
Responsibilities
• Design and deploy real-time conversational modules (Real-time Voice AI, STT/TTS, LLM orchestration) integrated with telephony infrastructure (Telephony APIs / PSTN / WebRTC).
• Build and optimize contextual memory layers (Vector DBs, Graph Memory) that enable the system to recall patient preferences, key relationships, and historical topics across multiple phone calls.
• Develop analytical logic to analyze patient interviews for shifts in mood, tone, cognitive patterns, and overall emotional well-being.
• Build high-performance backend microservices (Python) alongside intuitive web interfaces and analytics dashboards for caregivers and medical staff (React / TypeScript).
• Ensure strict adherence to health data security standards (HIPAA compliance) and optimize end-to-end streaming latency for natural voice interactions.
Requirements
• Experience: 4+ years of commercial software engineering experience using Python and JavaScript/TypeScript in production environments.
• Core Tech Stack & Ecosystems:

Backend & Cloud: Python (FastAPI, WebSockets, AsyncIO), PostgreSQL, Redis

• AI & Voice Stack: LLM APIs (OpenAI, Claude), Real-time Voice Agents, Speech-to-Text (STT) & Text-to-Speech (TTS) models, Vector Databases (Pinecone, Qdrant, ChromaDB, Weaviate), LangChain / LlamaIndex
• Telephony & Real-Time Media: Telephony API integrations (e.g., Twilio, LiveKit, Vapi, Retell AI)
• Frontend: React.js, TypeScript, Tailwind CSS (for administrative & analytics dashboards)
• DevOps & Infrastructure: Docker, AWS / GCP, CI/CD, real-time audio latency monitoring
• Nice to Have:
• Experience in HealthTech / MedTech environments (familiarity with HIPAA / SOC2 standards).
• Background in audio signal processing, vocal tone analysis, or sentiment/cognitive analysis.

•

Recognized Certifications (Highly desirable):
• AWS Certified Developer – Associate / AWS Certified Machine Learning – Specialty
• Google Cloud Professional Data Engineer / Developer Certification
• Recognized Certifications in AI & LLM Engineering