Senior AI Backend Engineer

K Health; Illinois; On-site; USD 150,000 - 190,000; Full time

Job summary

K Health is hiring a Senior Backend Engineer to join our AI Engineering team in the United States. You will design and build scalable backend services and APIs powering intelligent systems, collaborating with data scientists, ML engineers, and product managers.

You will work with a hybrid model stack including OpenAI, Google Gemini, and self-hosted LLMs, and integrate with clinical systems (FHIR/EMR). A strong background in distributed systems and observability is essential.

Qualifications

• 6+ years of backend engineering experience with proficiency in multiple languages (Python/Java/Go/Rust/Kotlin).
• Solid understanding of AI systems architecture and LLM/inference pipelines.
• Proven experience building & scaling backend APIs, microservices, and background jobs.

Responsibilities

• Build and maintain reliable, scalable backend services for AI agent execution and orchestration.
• Develop AI agent systems for complex workflows using LangChain, LangGraph, LiteLLM, Langfuse.
• Orchestrate hybrid model stacks with OpenAI, Google Gemini, and self-hosted LLMs.
• Integrate with clinical systems (FHIR, EMR) and ensure observability with OpenTelemetry and Datadog.
• Design APIs (GraphQL, REST), workers, and event-driven systems interfacing with AI inference engines.
• Collaborate with Data Science, ML, and engineering teams to deploy AI features and improve backend performance.

Skills

Backend languages

AI systems

APIs

Databases

Distributed systems

Team collaboration

Tools

PostgreSQL

MySQL

MongoDB

Redis

RabbitMQ

Job description

About the role:

We are seeking a Senior Backend Engineer with deep backend engineering expertise and proficiency in one or more major programming languages (e.g., Python, Java, Go, Rust, or Kotlin), along with a strong understanding of AI models and agents. As a core member of our AI Engineering team, you will collaborate with data scientists, ML engineers, and product managers to build scalable, production-ready infrastructure and APIs that power intelligent systems.

What you'll be doing:

As a Senior Backend Engineer in the AI Engineering team, you will:

• Build and maintain reliable, scalable backend services to support AI agent execution and orchestration.
• Develop AI agent systems for complex operational workflows using LangChain, LangGraph, LiteLLM, and Langfuse.
• Orchestrate a hybrid model stack that includes OpenAI and Google Gemini alongside self-hosted and fine-tuned LLMs like Gemma and Llama.
• Build and maintain integrations with clinical systems (FHIR, EMR).
• Drive observability and reliability using OpenTelemetry, Datadog, and Langfuse.
• Design APIs (GraphQL, REST), background workers, and event-driven systems that interface with AI inference engines and agent runtimes.
• Collaborate with Data Science, ML, and engineering teams to deploy AI features and improve the performance, scalability, and reliability of backend systems.
• Participate in code reviews, knowledge sharing, and mentoring to elevate the team’s technical capabilities.

What we’re looking for:

• 6+ years of backend engineering experience, with strong proficiency in more than one major programming language (such as Python, Java, Go, Rust, or Kotlin).
• Solid understanding of AI systems architecture and experience working in environments involving AI agents, LLMs, or inference pipelines.
• Proven experience in building and scaling backend APIs, microservices, and background jobs.
• Strong experience with relational and NoSQL databases (e.g., PostgreSQL, MySQL, MongoDB, Redis), including schema design, data modeling, and query optimization.
• Experience with message brokers and distributed systems (e.g., Pub/Sub, Redis Streams, RabbitMQ).
• Highly adaptable, a strong team player, with the ability to quickly learn and apply new technologies.

Advantages:

• Strong proficiency in Python and/or Node.js/NestJS.
• Experience with clinical systems and healthcare data standards (FHIR, EMR/EHR).
• Hands-on experience with AI agent frameworks such as LangChain, LangGraph, or LiteLLM.
• Experience orchestrating hybrid model stacks combining commercial APIs (OpenAI, Google Gemini) with self-hosted or fine-tuned LLMs.
• Familiarity with observability tools for AI systems (Langfuse, OpenTelemetry).

Who We Are:

Behind every leading health system is K Health’s AI-powered virtual care engine.

Our deeply integrated model modernizes the primary care loop by using AI to put humans first. For our patients, we offer clinical AI (i.e., PatientGPT) and unparalleled access to close care gaps around the clock. For our Providers, we deliver provider-serving agentic solutions (i.e., Perfect Note) to eliminate administrative overload and burnout. And for the health systems, we deploy our top-grade Virtualists in AI-powered virtual clinics 24/7 to capture the patients' care journeys at step one, retain the journey through the system for longitudinal care, and strengthen profitability.

We’re founded in 2016, headquartered in New York City, and backed by over $443.5M from leading investors including Valor Equity Partners, Claure Group, Mangrove Capital Partners, 14W, Notable Capital, Lerer Hippeau, Primary Venture Partners, Comcast Ventures, PICO Venture Partners, Max Ventures, and other strategic healthcare partners.

We offer competitive compensation packages based on industry benchmarks for function, level, and geographic location. Offer amounts are determined by multiple factors such as a candidate's experience and expertise.

We are proud to be an Equal Opportunity Employer and consider applicants for employment regardless of race, ethnicity, religion, color, national origin, ancestry, disability, medical condition, genetic information, marital status, sex, gender, gender identity, gender expression, sexual orientation, pregnancy, childbirth and breastfeeding, age, citizenship, military or veteran status, or any other class protected by applicable federal, state, and local laws. We’re deeply committed to building teams as diverse as the patients we serve and strive to cultivate an environment where everyone can bring their most authentic self to work. We depend on our differences to make our team stronger, our workplace more dynamic, and our product accessible to all of our users.