Senior AI Software Engineer (Agentic Systems & LLM Infrastructure)

Function Health; United States; On-site; USD 120,000 - 160,000; Full time

Benefits offered by this job

Competitive compensation

Equity

Health benefits

Job summary

A leading health tech company in the United States is looking for a Senior AI Software Engineer to design and develop production-grade AI systems. The ideal candidate will have over 5 years of experience in backend systems, expertise in distributed architecture, and a strong grasp of AI/ML infrastructure. Join a fast-paced team and work on impactful health solutions. Competitive compensation, equity, and benefits offered.

Qualifications

• 5+ years of experience building production-grade backend systems.
• Deep experience with microservices and event-driven architecture.
• Proficiency with telemetry, monitoring, and production issue triage.

Responsibilities

• Design and build distributed backend systems for LLMs and AI infrastructure.
• Integrate AI/LLM models into product systems.
• Collaborate with teams to translate cutting-edge AI into production.

Skills

Python

Distributed systems

Backend infrastructure

AI/ML infrastructure

API design

Communication skills

Tools

Kubernetes

Docker

Terraform

Job description

Overview

Senior AI Software Engineer (Agentic Systems & LLM Infrastructure) role at Function Health.

Join Function Health to apply for the Senior AI Software Engineer role focused on agentic systems, LLM infrastructure, and production-grade AI deployments. Function Health builds technology to improve health outcomes and is backed by notable investors and awards.

Role Overview

As a Senior AI Software Engineer, you will own the design and development of end-to-end AI systems, spanning backend infrastructure, model orchestration, and production-grade deployment. You’ll collaborate with product, data, and infrastructure teams to integrate LLMs, agentic frameworks (LangGraph, LangChain, AutoGen), computer vision models, and vector-based reasoning systems into consumer-facing and internal tools. The role is highly technical, hands-on, and requires both deep systems expertise and practical AI application skills.

Key Responsibilities

• Design, build, and scale distributed backend systems that power LLMs, agents, and AI infrastructure.
• Integrate AI/LLM models into product systems (e.g., LangGraph, Agentic APIs, vector stores, orchestration layers).
• Develop high-reliability APIs and services for real-time AI inference, telemetry, usage metering, and monitoring.
• Own backend architecture decisions across authentication, billing, deployments, and developer platforms.
• Collaborate with product, infra, and research teams to translate cutting-edge AI into production systems.
• Ensure production-readiness through observability, CI/CD pipelines, and SRE-style reliability engineering.
• Drive continuous improvement, pushing for faster iteration, scalability, and throughput.
• Mentor peers and lead by example with a hands-on, high-ownership, startup-style mindset.

Must-Have Qualifications

• 5+ years of experience building production-grade backend systems in Python, Go, or similar.
• Deep experience with distributed systems, microservices, and event-driven architecture.
• Strong grasp of AI/ML infrastructure, model inference, model serving, and agentic frameworks.
• PostgreSQL, Redis, or similar data store expertise, including performance tuning and scaling.
• Familiarity with vector databases, embeddings, and LLM-specific storage/search systems.
• Experience deploying in cloud-native environments (AWS, GCP) using Kubernetes, Terraform, Docker.
• Proficiency with API design, backend frameworks (e.g., FastAPI, Flask), and load balancing.
• Hands-on experience with telemetry, monitoring, logging, and production issue triage.
• Understanding of CI/CD workflows, developer tooling, and test automation at scale.
• Ability to work in fast-paced, early-stage environments, making tradeoffs and shipping quickly.
• Strong communication skills: clear, concise, and collaborative—even when disagreeing.
• Bias for action: you’re a scrappy problem solver who thrives in ambiguity.

Nice-to-Have Qualifications

• Experience with LangChain, LangGraph, AutoGen, OpenAI APIs, or other agent-based orchestration frameworks.
• Familiarity with computer vision models and multimodal AI systems.
• Background in health tech, regulated data systems (HIPAA compliance), or medical data pipelines.
• Experience building AI-powered consumer applications with personalization and real-time inference.
• Exposure to reinforcement learning, retrieval-augmented generation (RAG), or long-term memory agents.
• Motivated by a mission-driven product, with excitement for being part of explosive growth.
• Background in competitive sports, military, or other high-intensity, high-throughput environments where resilience and ownership are key.

Why Join Us

• Work on cutting-edge AI products that directly help people improve their health.
• Build agentic systems from the ground up, influencing technical strategy and architecture.
• Join a fast-moving, high-ownership team, with significant autonomy and impact.
• Competitive compensation, equity, and benefits in a rapidly scaling health tech company.

At Function, we celebrate diversity and are committed to building a diverse and inclusive workforce. We are an equal opportunity employer and do not discriminate on race, color, gender identity, ancestry, religion, age, sexual orientation, national origin, disability, marital status, Veteran status, or any other occupationally irrelevant criteria.

Join the Function Health team and become a part of our mission to build a healthier future for all. Learn more about us at Function Health.

Important: Legitimate communications from the Function Health team will come from an email address ending in @functionhealth.com. Function Health will never request personal information such as banking details during the hiring process. If you have doubts about a communication, contact [e-mail].