• Own the end-to-end technical direction and architectural patterns for high-impact GenAI initiatives • Establish and evolve the CI/CD and automated evaluation pipelines for non-deterministic AI outputs • Lead the evaluation and prototyping of cutting-edge techniques for AI roadmap decisions • Implement sophisticated observability hooks and monitoring strategies to trace agent logic • Drive the experimentation loops required to hit aggressive accuracy, latency, and cost targets • Act as the principal design authority and code reviewer for the team, mentoring engineers and championing secure-by-design practices

• Architect and code sophisticated AI modules, including high-performance embedding pipelines, custom chunkers, and advanced retrieval evaluators • Lead the integration of intelligent agent services with diverse internal and external APIs and vector databases • Stay at the bleeding edge of AI research, implementing the latest advancements in fine-tuning, RLHF, and prompt engineering frameworks • Drive agile excellence by spearheading sprint deliveries and collaborating with cross-functional leaders • Champion code quality and team growth by performing high-level peer reviews • Architect and implement modular, cloud-native microservices that integrate GenAI into our production ecosystem • Take ownership of the production lifecycle by building robust CI/CD pipelines • Drive technical excellence by developing comprehensive evaluation suites

• Architect and code sophisticated AI modules, including high-performance embedding pipelines, custom chunkers, and advanced retrieval evaluators • Lead the integration of intelligent agent services with diverse internal and external APIs and vector databases to solve complex, cross-service challenges • Stay at the bleeding edge of AI research, implementing the latest advancements in fine-tuning, RLHF, and prompt engineering frameworks like DSPy • Drive agile excellence by spearheading sprint deliveries and collaborating with cross-functional leaders to define the scope of transformative AI features • Champion code quality and team growth by performing high-level peer reviews and contributing to shared utility libraries that boost development velocity • Architect and implement modular, cloud-native microservices that integrate GenAI into our production ecosystem, ensuring our Agentic solutions are as scalable and reliable as they are intelligent • Take ownership of the production lifecycle by building robust CI/CD pipelines and using observability frameworks (like Datadog or Databricks) to monitor model health, trace agent logic, and ensure system uptime • Drive technical excellence by developing comprehensive evaluation suites—incorporating both traditional testing and modern LLM-based evals—to benchmark accuracy, safety, and performance before every release

This is a remote position. Job Title: Applied AI Engineer (Mid-Senior) Role Summary The Mid-Senior Applied AI Engineer is responsible for designing, developing, and deploying scalable artificial intelligence solutions within an enterprise AI platform. Moving beyond basic implementation, this role requires architectural thinking to build robust GenAI services, complex retrieval pipelines (RAG), and agentic workflows. The engineer will partner closely with AI Program Management, Data & Analytics, and business stakeholders to translate validated business requirements into secure, production-ready AI applications. Key Responsibilities - Platform Development: Design and build core AI application components supporting enterprise AI initiatives, including agentic workflows, batch processing, and data integrations. - Advanced Retrieval & Agentic Architectures: Implement and optimize sophisticated embeddings, vector search strategies, and multi-agent workflows to handle both text and structured data retrieval from core enterprise systems. - API & Backend Engineering: Develop secure, high-performance backend APIs (primarily FastAPI/Python) to facilitate seamless integration between foundational models and internal enterprise architecture. - Model Integration & Orchestration: Work with multiple LLMs (OpenAI, Claude, Gemini) via model-agnostic routing layers, optimizing for cost, latency, and task-specific performance. - Feasibility & Scoping: Collaborate directly with AI Program Managers and Business Analysts during the intake phase to assess technical feasibility, architecture requirements (e.g., Agentic vs. Standard ML), and data readiness for new business requests. - Deployment & LLMOps: Drive the deployment of AI systems, establishing CI/CD pipelines, containerization, and robust LLM monitoring (observability, prompt drift, and accuracy metrics). - Governance & Compliance: Ensure all AI components strictly adhere to enterprise AI governance, security, and data privacy standards. - Mentorship: Provide technical guidance and code reviews for junior developers on the team. Required Technology Stack - AI Models: Deep familiarity with API integration and prompting for OpenAI, Anthropic (Claude), and Google (Gemini) models. - Frameworks: Advanced proficiency in LangChain, LangGraph, and LlamaIndex for building RAG pipelines and agentic decisioning systems. - Backend & APIs: Strong expertise in Python and FastAPI. Basic working knowledge of Node.js. - Data Architecture: Experience designing schemas and optimizing queries for Vector Databases (e.g., Azure AI Search, Pinecone, Milvus) and relational databases (PostgreSQL). - Cloud Infrastructure: Hands-on experience with Azure Cloud and Azure AI Services. - DevOps & Deployment: Proficiency with Git, Docker, and CI/CD principles. Experience with LLM observability tools is highly preferred.