Senior AI Engineer

📋 Description

• • Design and implement production-grade agentic systems using LLMs to autonomously reason, use tools, manage context, and orchestrate multi-step workflows for platform users.
• • Build scalable backend services, APIs, and data pipelines that support real-time AI inference, conversation state management, and tool execution with robust error handling and recovery mechanisms.
• • Architect AI infrastructure to handle growing inference demands, increasing agent complexity, and strict production reliability requirements on AWS.
• • Develop and maintain RAG pipelines including embeddings generation, vector search indexing, and retrieval strategies to enable knowledge-driven AI responses within the Commerce7 platform.
• • Apply foundational machine learning knowledge to inform decisions on model selection, fine-tuning, embedding techniques, and evaluation metrics, determining when to use off-the-shelf models versus custom training approaches.
• • Collaborate with product, engineering, DevOps, and QA teams to define requirements, prioritize features, and lead technical execution of AI-powered capabilities from concept to production.
• • Evaluate emerging agentic frameworks, LLM providers, and AI tooling to recommend and adopt innovations that advance the team’s technical capabilities and product outcomes.
• • Establish and document engineering standards for AI systems covering reliability, safety, observability, prompt management, and version control of AI artifacts.
• • Write clean, well-tested, and maintainable code following SOLID principles, conduct thorough code reviews, and champion best practices in software development across the engineering team.
• • Implement reliability patterns for non-deterministic AI systems including guardrails, input sanitization, output validation, and fallback strategies to ensure safe and consistent user experiences.
• • Integrate LLM functionality using prompt engineering, function calling, and context management techniques to enable precise and context-aware agent behavior.
• • Design database architectures spanning relational databases and vector stores to support efficient storage, retrieval, and scaling of structured and semantic data.
• • Optimize system performance through async programming, concurrency management, caching strategies, and latency reduction techniques for real-time AI interactions.
• • Ensure production readiness through CI/CD pipelines, monitoring, logging, alerting, and observability tooling to maintain high availability and rapid incident response.
• • Drive independent ownership of AI projects with minimal supervision, from requirements gathering and architecture design through deployment, iteration, and operational maintenance.