Lead Backend Engineer

Alldus; New York (NY); On-site; USD 220,000 - 300,000; Full time

Benefits offered by this job

Impactful healthcare work

Novel AI product environment

Ownership of real production systems

Collaborative ML engineering team

Job summary

Alldus is supporting a health-tech startup building real-time AI architecture for clinical neurology. You will design and implement scalable Python/Go services for processing live biometric data and deploying ML models in production.

You’ll own reliability and performance, craft high-throughput data pipelines, and build APIs powering critical workflows, working closely with ML engineers. In-office in NYC with US work authorization.

Qualifications

• 5+ years building and operating backend systems in production.
• Experience with event-driven / stream-processing systems.
• Proficient in Python with concurrency and testing.
• Containerization and orchestration, preferably Kubernetes.
• Strong relational database design and query performance.

Responsibilities

• Build scalable Python/Go services for real-time clinical data processing.
• Design high-throughput data pipelines and time-series models.
• Develop APIs powering critical clinical workflows.
• Deploy and maintain ML models in production.
• Own system reliability, monitoring and performance.
• Contribute to secure, compliant software for regulated healthcare environments.

Skills

Backend systems

Event-driven architecture

Stream processing

Python

Python concurrency

Kubernetes

Relational databases

Tools

Kubernetes

Job description

Our client is a highly funded, early-stage health-tech venture developing next-generation AI architecture for clinical neurology. The company creates advanced deep learning systems trained on massive biometric datasets to track central nervous system health in acute care environments.

The platform analyses continuous physiological streams in real time, detecting anomalies and critical neurological events instantly to alert critical care teams and streamline diagnostics.

You’ll build the infrastructure behind it

• Build scalable Python/Go services for real-time clinical data processing
• Design high-throughput data pipelines, time-series models and retention
• Develop APIs powering critical clinical workflows
• Deploy and maintain ML models in production
• Own system reliability, monitoring and performance
• Contribute to secure, compliant software for regulated healthcare environments

What’s in it for you:

• Work that matters: real patients and real outcomes in a clinical setting
• A genuinely novel AI product, with the chance to shape the platform around it
• Full ownership of problems, from a vague brief to a live, well-monitored service
• Day-to-day collaboration with ML engineers, turning research into dependable production systems

$220-300k base · In-office, NYC (5 days a week, some travel to customer sites). Must have US work authorisation

Who you are:

• 5+ years of building and operating backend systems in production
• You can own a problem from an ambiguous start to a running, monitored service, and you can explain your decisions verbally and in writing.
• Real experience with event-driven or stream-processing systems: partitioning, checkpointing, backpressure, and at-least-once delivery.
• Python, including concurrency (threads vs. processes, asyncio) and testing.
• Proficiency with containerization and orchestration, preferably using kubernetes.
• Solid relational database skills, from schema design to query performance.

If you want to point at the product a year from now and say "I built that", let’s talk.