Developer, LLM & AI PLATFORMS

Title: Developer, LLM & AI Platform

Supervisor: Chief Technology Officer

Position Summary

The Developer, LLM & AI Platform is responsible for leading the design, development, and production deployment of Large Language Model (LLM)-powered capabilities across RS21’s product and services portfolio, with a primary focus on Prequip, RS21’s AI-powered predictive maintenance platform.

This role serves as the technical owner of LLM integration, translating product and business requirements into scalable, secure, and reliable AI-driven features. Working closely with Data Engineering, Product, and Platform teams, the Developer ensures LLMs are implemented responsibly, performantly, and in alignment with RS21’s data readiness and cloud-first strategy.

As a member of RS21’s technical staff, this role helps shape AI architecture standards, advances internal LLM best practices, and contributes to RS21’s long-term AI roadmap.

Key Responsibilities

LLM Architecture & Development

• Design, build, and deploy LLM-powered services and features using leading providers (e.g., AWS Bedrock, OpenAI, Anthropic).
• Own prompt engineering strategies, including prompt design, versioning, testing, and optimization.
• Implement Retrieval-Augmented Generation (RAG) workflows in collaboration with Data Engineers.
• Develop multi-step reasoning, tool-calling, and agent-based LLM workflows where appropriate.
• Ensure LLM integrations are production-ready, scalable, and secure.

AI Product Enablement

• Translate product and user requirements into intelligent, explainable AI features.
• Build APIs and backend services that expose LLM capabilities to internal and external consumers.
• Support natural language interfaces that surface insights from predictive maintenance, operational, and asset data.
• Partner with Product and UX teams to ensure AI features are usable, trustworthy, and aligned with customer needs.

Evaluation, Reliability & Governance

• Implement evaluation frameworks to measure LLM accuracy, relevance, latency, and cost.
• Design and enforce guardrails to mitigate hallucinations, bias, and unsafe outputs.
• Monitor and optimize LLM usage for performance, scalability, and cost efficiency.
• Support observability and logging for AI systems in production.

Cross-Functional Collaboration

• Collaborate closely with Data Engineers to ensure LLMs are powered by high-quality, well-structured data.
• Partner with cloud and platform teams to deploy AI services within AWS environments.
• Contribute to internal documentation, standards, and best practices for LLM and AI development.
• Provide technical guidance and mentorship related to LLM patterns and emerging AI capabilities.

Qualifications

• Bachelor’s degree or equivalent experience in computer science, engineering, or a related field.
• 5+ years of software development experience, with a strong backend focus.
• Demonstrated hands-on experience building and deploying LLM-powered applications.
• Deep understanding of prompt engineering, RAG architectures, and LLM inference workflows.
• Experience developing APIs and services in a cloud environment (AWS preferred).
• Strong system design skills and ability to reason through architectural tradeoffs.
• Proven ability to move AI features from prototype to production.
• Experience with AWS AI services (e.g., Bedrock, Lambda, ECS, EKS).
• Familiarity with vector databases and embedding-based retrieval systems.
• Exposure to MLOps, AI evaluation, or AI governance frameworks.
• Experience supporting AI features tied to analytics, predictive modeling, or real-time data.
• Experience working in product-focused or data-driven organizations.