Senior Backend AI Engineer — Real-Time Healthcare Platform

North American Dental Group; Lisboa; In loco; EUR 60.000 - 90.000; Tempo pieno

Descrizione del lavoro

About UpHill

At UpHill, our mission is to increase clinical capacity so healthcare professionals can focus on what matters most — the patients. Healthcare teams are either stretched thin by work that can be automated or weighed down by waste that can be avoided. UpHill's intelligent automated platform uses hospital data and patient conversations to turn chaos into useful and efficient interactions.

We build conversational AI agents, intelligent clinical pathways, and care orchestration tools that empower clinicians to work at their full potential — deployed across leading hospitals in Europe, with 100K+ lives impacted and over 1 million clinical interactions mediated. UpHill Route is a certified Class IIa Medical Device.

We're a team of curious and creative people who believe technology should enhance — not replace — the work of healthcare professionals. If you're excited about making a real impact in one of the most meaningful industries in the world, you just might be an Uphiller.

Today we're looking for a Senior Backend Developer to join our AI team and help us build the next generation of AI infrastructure for healthcare — powering clinical agents that interact with patients in real time, triage symptoms intelligently, and support clinical decision‑making at scale.

Stack Used

• Python AI frameworks (e.g., LangChain and similar LLM orchestration tools)
• AWS stack — ECS/Fargate (service architecture), SQS, EventBridge, S3, Bedrock — Terraform
• PostgreSQL · Redis
• Docker · GitHub Actions

Responsibilities

• Design and build AI agent pipelines: Work closely with the engineering team to translate product and clinical requirements into reliable, production‑grade services powering real‑time patient interactions.
• Develop and maintain backend microservices: Write clean, well‑tested, maintainable code. Ensure services are performant, scalable, and production‑ready from day one.
• Contribute to AWS cloud infrastructure: Participate in designing, deploying, and maintaining the AWS infrastructure supporting the platform — ECS clusters, SQS queues, EventBridge rules, and more.
• Build and evolve internal tooling: Contribute to the shared SDK that other agents and services are built upon — raising the bar for consistency, reliability, and developer experience across the platform.
• Showcase implemented solutions: Communicate and demonstrate technical solutions during sprint reviews, including design choices, trade‑offs, and how the work ties back to product goals.
• Define and uphold engineering conventions: Collaborate with the team to establish coding standards, review practices, and architectural patterns — then enforce them through code review and tooling.
• Ownership mentality: You ship and maintain what you build.
• Autonomous but collaborative: Capable of owning initiatives while working effectively with cross‑functional teams (product, clinical, ops, etc.).
• Product‑focused: You care about the why as much as the how behind every feature.

Main Requirements

• MSc/BSc in Computer Engineering, Software Engineering, or a related field
• Minimum 5 years of backend development experience in production environments
• Strong proficiency in Python
• Experience building and integrating LLM‑powered applications using Python AI frameworks (LangChain, LlamaIndex, or equivalent)
• Experience in event‑driven architecture — SQS, Kafka, or similar message queues
• Experience with AWS services: ECS/Fargate, S3, SQS, EventBridge, AI services
• Proficiency with PostgreSQL and Redis
• Strong testing experience — Unit, Integration, E2E
• Rigorous about code quality
• Experience taking part in architectural discussions and decisions
• Keen awareness of the evolving AI landscape, including LLM integrations and agent patterns in day‑to‑day engineering work
• Strong observability mindset: familiarity with tools like Datadog, CloudWatch, or OpenTelemetry — understands the importance of logging, metrics, and alerting in a production‑grade SaaS product
• Fluency in English

Strong Plus

• Previous experience deploying Voice AI agents at scale is a strong plus.
• Terraform or other Infrastructure‑as‑Code tools
• Experience with real‑time streaming or WebSocket‑based systems
• Background in healthcare, medical devices, or regulated industries
• HL7v2 / FHIR knowledge
• Experience with Java / Spring Boot services

What You’ll Get

• Be part of a dynamic, mission‑driven team shaping the future of healthcare
• Competitive salary
• Comprehensive health insurance
• Top‑tier equipment — new MacBook + budget for peripherals
• Flexible schedule and hybrid work model
• Direct impact on patient outcomes — the AI you build handles real clinical conversations
• No‑BS culture: small, senior team where your voice shapes product and architecture decisions