Lead - Artificial Engineer

The AI Systems Developer will design, develop, and maintain production-ready AI systems using Large Language Models (LLMs), AI agents, retrieval-augmented generation (RAG), and workflow orchestration. The role focuses on building reliable AI applications, integrating model APIs and external tools, evaluating AI output quality, implementing guardrails, and ensuring security, compliance, and operational stability.

Roles and Responsibilities

• Design, develop, and maintain AI agent workflows, pipelines, and reusable AI skills.

• Build prompt architectures, system instructions, and context assembly strategies.

• Develop RAG pipelines, including document ingestion, chunking, embeddings, indexing, and retrieval optimization.

• Integrate LLM providers, APIs, tool/function calling, MCP servers, and external platforms such as Atlassian.

• Develop supporting applications, APIs, background processes, and state management.

• Create evaluation frameworks to measure accuracy, groundedness, regression, latency, and cost.

• Implement AI guardrails, input validation, prompt-injection protection, and human-in-the-loop reviews.

• Set up logging, tracing, and monitoring to troubleshoot AI outputs and system failures.

• Manage token usage, model selection, and workload costs.

• Ensure data protection, access control, secrets management, and compliance with HIPAA requirements.

• Collaborate with developers, architects, business analysts, and QA teams in an Agile environment.

• Maintain technical documentation, participate in code reviews, and contribute to AI engineering standards.

• Programming: Python and/or TypeScript/JavaScript.

• Generative AI & LLMs: LLM APIs, prompt engineering, tool calling, and function calling.

• RAG & Retrieval: Retrieval architectures, embeddings, vector search, and retrieval quality tuning.

• AI Agent Development: Agent workflows, multi-step orchestration, and reusable AI skills.

• API & Backend Development: API design, background processing, and state management.

• Database: Relational databases and SQL.

• Cloud: Microsoft Azure, managed services, identity, and secrets management.

• DevOps & Version Control: Git and CI/CD.

• AI Evaluation & Monitoring: Accuracy testing, regression testing, tracing, logging, monitoring, latency, and cost optimization.

• AI Security: Input/output validation, prompt-injection protection, access control, and safe failure handling.