AI Engineer at Unify Consulting in Seattle

Summary: Unify Consulting is a leading AI management consulting firm designed to help clients overcome challenges and achieve their goals through an agile approach. They are seeking an AI Engineer to design and build LLM-powered applications and agentic systems that interact with enterprise systems, focusing on quality and user feedback. Responsibilities: - Build GenAI / LLM applications - Design and develop LLM-powered applications using enterprise AI platforms (e.g., AWS Bedrock, Azure OpenAI / Azure AI platforms, Google Vertex AI) - Implement multi-step orchestration workflows that translate user intent into reliable actions and explainable outputs - Build robust RAG pipelines (vector databases, embeddings, chunking strategies) and validate grounding quality - Design agent reasoning/control patterns (e.g., planning vs execution separation, tool calling, memory/context management) - Integrate agents with tools/APIs and enterprise workflows with appropriate governance and guardrails - Create reusable prompt templates/libraries; implement prompt testing frameworks; establish prompt versioning/governance - Evaluate solutions for quality/safety/latency/cost and iterate quickly - Partner with platform/LLMOps teammates to deploy, monitor, and improve LLM systems in production - Build observability and reliability mechanisms for agent-based workflows - Lead technical discovery, map workflows/pain points, and communicate solutions to technical and executive stakeholders Required Qualifications: - 1–2+ years hands-on GenAI / Agentic AI experience building LLM apps on enterprise platforms (AWS Bedrock / Vertex AI / Azure AI platforms) in a professional setting - Strong backend engineering experience (Python preferred) delivering production-grade systems - Hands on professional experience with RAG patterns and implementation - Ability to communicate clearly and contribute in fast-moving, cross-functional teams - Computer Science / strong CS fundamentals Preferred Qualifications: - Applied Scientist style skills: deep learning/NLP with PyTorch/TensorFlow + Hugging Face; ability to interpret research and implement emerging techniques - Fine-tuning and optimization methods (LoRA/PEFT/QLoRA), distillation/quantization/pruning, GPU memory optimization - Experience building secure tool integrations / agent middleware (tool schemas, SaaS integrations like Salesforce/SAP/ServiceNow, OAuth2, API security) - Evaluation harnesses and regression testing for prompts/agents; RAG quality testing - Cloud-native experience in large enterprise environments Required Skills: GenAI, Agentic AI, LLM applications, Enterprise AI platforms, AWS Bedrock, Azure OpenAI, Azure AI platforms, Google Vertex AI, RAG patterns, Backend engineering, Python, Computer Science fundamentals