Ruby on Rails Developer (AI Focused) USA

Remotestar; Houston (TX); Hybrid; USD 100,000 - 130,000; Full time

Job summary

RemoteStar is seeking a Software Engineer to enhance their AI capabilities in Houston, TX. The role involves designing and implementing AI-driven features within a growing SaaS platform. Candidates should have over 3 years of experience in backend engineering, particularly with RoR or Golang, and familiarity with ML tools. Strong problem-solving skills and the ability to work independently in a quick-moving environment are essential. This hands-on position requires a builder mindset to turn ideas into features rapidly.

Qualifications

• 3+ years of experience as a software engineer in a SaaS or cloud-based environment.
• Hands-on experience with AI/ML tools like OpenAI, Anthropic, or Hugging Face.
• Strong understanding of performance optimization in distributed systems.

Responsibilities

• Design and implement AI-powered features within the platform.
• Integrate LLMs and/or ML models into existing services.
• Collaborate with Product to solve business problems using AI.

Skills

Backend engineering

AI/ML tools

API integration

Data flow understanding

Problem-solving skills

Tools

RoR

Golang

SQL Server

Kubernetes

Azure

Job description

AtRemoteStar, we're currently hiring for one of our clients based in Houston, TX.

Years of experience: 3 to 5 years

Location: USA

About Client

A fast-growing US-based SaaS company is transforming how energy firms manage operations. Their end-to-end ERP platform streamlines field data, production, finance, land, and compliance, delivering real-time insights and operational efficiency. With a strong client base and innovative tech, they’re redefining digital transformation in the energy and utilities sector.

You’ll design and implement AI-driven functionality that improves automation and user experience. This includes leveraging LLMs, machine learning models, and modern AI tooling within a production SaaS environment.

This is a hands‑on role for someone who can move quickly, make pragmatic decisions, and bring AI concepts into real, scalable product features.

Responsibilities

• Design and implement AI-powered features within the platform (e.g., automation, recommendations, copilots)
• Integrate LLMs and/or ML models into existing services and workflows
• Evaluate, select, and optimize AI tools, APIs, and frameworks for production use
• Collaborate with Product to translate business problems into AI-driven solutions
• Build and maintain scalable backend services to support AI functionality
• Profile, test, and optimize performance of AI-integrated systems
• Ensure reliability, security, and cost‑efficiency of AI components in production
• Contribute to architecture decisions around AI integration and system design
• Partner with engineering teams to embed AI into existing applications without degrading stability

Requirements

• 3+ years of experience as a software engineer in a SaaS or cloud-based environment
• Strong backend engineering experience (RoR and/or Golang preferred)
• Experience integrating APIs and working within distributed systems
• Hands‑on experience with AI/ML tools (e.g., OpenAI, Anthropic, Hugging Face, or similar)
• Experience building or integrating AI-powered features into applications (not just experimentation)
• Strong understanding of data flow, system design, and performance optimization
• Experience with relational databases (SQL Server or similar)
• Familiarity with microservices architecture, Kubernetes, and CI/CD pipelines
• Experience deploying applications in Azure or similar cloud environments
• Strong problem‑solving skills with ability to work in ambiguous, fast-moving environments
• Builder mindset—someone who can take an idea and turn it into a working feature quickly
• Pragmatic approach to AI (focus on value, not hype)
• Ability to work independently in a contract environment while collaborating closely with internal teams
• Strong communication skills and ability to explain AI concepts to non‑technical stakeholders

Preferred

• Experience with prompt engineering, embeddings, or retrieval-augmented generation (RAG)
• Exposure to model evaluation, fine‑tuning, or AI performance monitoring
• Experience with event‑driven architectures or real‑time data processing
• Background in energy, fintech, or other complex data-driven industries