cover image
Yuma AI (YC W23)

Yuma AI (YC W23)

yuma.ai

1 Job

25 Employees

About the Company

Yuma is using the latest AI breakthrough to automate customer service for large Shopify merchants. We provide Auto-Pilot agents that can fully resolve and handle support tickets, including confirming or taking actions in external services, enabling true automation.

Listed Jobs

Company background Company brand
Company Name
Yuma AI (YC W23)
Job Title
AI Product Focus - Senior Full Stack/Rails Engineer (Boston)
Job Description
**Job Title** Senior Full Stack/Rails Engineer **Role Summary** Lead the architecture, development, and scaling of Yuma AI’s core Ruby on Rails platform while integrating and optimizing large language model (LLM) capabilities. Drive end‑to‑end product delivery from backend building, AI pipeline design, to occasional frontend tasks, ensuring high performance, reliability, and rapid feature iteration in a fast‑moving, high‑ownership environment. **Expatations** - 5–10+ years of production‑grade Rails experience, delivering scalable applications. - Proven expertise in PostgreSQL, Redis, Sidekiq, and performance tuning of high‑throughput systems. - Hands‑on experience with LLM providers and AI‑agent workflows; comfortable handling non‑deterministic outputs. - Demonstrated ownership across the full product lifecycle and ability to ship iterative, data‑driven features at speed. - Strong communication, collaboration with founders/engineering, and willingness to work on frontend (Next.js/React) when necessary. **Key Responsibilities** 1. **Backend Engineering** - Design, implement, and scale large Ruby on Rails APIs. - Own critical subsystems: performance, reliability, maintainability. - Model and index PostgreSQL schemas; diagnose and resolve database bottlenecks. - Optimize Redis+Sidekiq pipelines for high‑throughput workloads. - Lead backend‑heavy feature projects from concept to deployment. 2. **AI/LLM Systems** - Integrate, evaluate, and iterate on LLM providers and models. - Build robust pipelines to manage LLM outputs safely and predictably. - Develop A/B tests, evaluation frameworks, and agentic workflows. - Optimize latency, reliability, and cost for LLM‑centric features. - Contribute to prompt engineering and AI system architecture. 3. **Product & Full‑Stack Contribution** - Collaborate closely with founders and product team to define requirements. - Participate in rapid product iterations: experimentation, data analysis, and feedback loops. - Ship end‑to‑end features when needed, including occasional frontend work in Next.js/React. - Maintain high product quality standards while accelerating delivery speed. **Required Skills** - Advanced Ruby on Rails proficiency (RESTful APIs, MVC, ActiveRecord). - Deep understanding of PostgreSQL (schema design, indexing, query optimization). - Expertise with Redis & Sidekiq for job processing. - Practical experience with LLM integration (OpenAI, Anthropic, Cohere, etc.) and AI‑agent pipelines. - Familiarity with performance monitoring, A/B testing, and telemetry. - Frontend basics (React/Next.js) for occasional feature support. - Strong analytical, problem‑solving, and communication skills. **Required Education & Certifications** - Bachelor’s degree in Computer Science, Software Engineering, or equivalent technical experience. - No mandatory certifications; relevant technical certifications (e.g., PostgreSQL, AWS, or AI/ML) are a plus.
Boston, United states
On site
Senior
18-12-2025