ZR_2807_JOB

Simple Solutions; San Francisco (CA); On-site; USD 140,000 - 190,000; Full time

Job summary

Artos in San Francisco (Mission Bay) is seeking an experienced backend engineer to design and scale AI-powered services. You will build APIs with Python frameworks, deploy containerized apps in AWS/GCP/Azure, and implement CI/CD pipelines.

The role emphasizes hands-on work with LLM-based applications, multi-step workflows, and prompt engineering to ship production-ready features. Ideal candidates have 3+ years of software development experience, a strong CS foundation, and comfort working in a

Qualifications

• Design and maintain scalable production-grade backend systems for AI apps.
• Orchestrate and evaluate LLM-based agents and chained workflows.
• Debug LLM-driven systems across model output, API, and logic.
• Conduct rapid experimentation and translate findings to production.
• Stay current with emerging AI models, practices, and tooling.
• Communicate clearly with technical and non-technical collaborators.
• Work effectively in a fast-paced startup environment.

Skills

Python

FastAPI

Django

AI/ML

API design

Cloud deployment

CI/CD

Infra-as-Code

Secure coding

LLM workflows

Prompt engineering

RAG pipelines

Education

Bachelor’s or Master’s in Computer Science, Engineering, or related field

Tools

GitHub Actions

AWS

GCP

Azure

Docker

Kubernetes

Terraform

Pulumi

OpenAI API

Anthropic

Job description

• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field (or equivalent practical experience)
• 3+ years of software development experience, with a focus on building and deploying AI/ML applications
• Building APIs from the ground up using Python frameworks such asFastAPIandDjango
• Deploying and scaling containerized applications in cloud environments (e.g.,AWS,GCP,Azure)
• Implementing CI/CD pipelines (e.g.,GitHub Actions)
• Working with Infrastructure-as-Code tools such asTerraformorPulumi
• Hands-on experience buildingLLM-based applications, including:
  • Designingmulti-step LLM workflowsand task-specific agents
  • Experience working with most frontier models (e.g. OpenAI, Anthropic, Google, etc.)
  • Experience with AI tools as a user, specifically AI code editors
  • Developing advancedprompt engineering strategies, evaluation frameworks, and RAG pipelines
  • Conductingtechnical R&Dto explore and define the boundaries of model functionality
• Familiarity withsecure coding practices, ideally in regulated industries (e.g., life sciences, healthcare, fintech)
• Experience working in or adjacent toregulated domains(life sciences, clinical R&D) is a plus
• Frontend development experience (e.g.,React) is a plus, but not required

Requirements

• Ability to design and maintain scalable, production-grade backend systems for AI applications
• Ability to create, orchestrate, and evaluateLLM-based agentsandchained workflowswith minimal oversight
• Ability to debug and improve LLM-driven systems, identifying issues across multiple layers (model output, API behavior, system logic)
• Ability to conduct rapid experimentation and research on LLM capabilities and translate findings into production functionality
• Ability tostay current with emerging practices, models, and tooling in the generative AI ecosystemand apply them pragmatically
• Ability to communicate clearly with technical and non-technical collaborators (e.g., product managers, medical writers, customer teams)
• Ability to operate effectively in a fast-paced, ambiguity-heavy environment, managing shifting priorities and novel problem spaces

Other Information

• Very comfortable working in a fast-paced and intense startup environment
• Willing to work in-person in our office in Mission Bay 4-5 days/week
• Likes matcha KitKats, believes every LLM prompt is just Schrodinger's cat waiting to be observed, and knows too many random facts about the Mongol postal system

Requirements

Why are you interested in Artos?

Have you successfully brought an LLM-based application to production for external customers?

Are you comfortable with a high-intensity "startup hours" environment (roughly 12-14 hours/day) to hit aggressive growth targets?

Legal/Compliance AI: Ironclad, Harvey.