AI Foundry Specialist

Job Description

AI Foundry Specialist

About the role
We're looking for an AI Foundry Specialist to configure and set up our document intelligence and document understanding capabilities. You'll be the subject-matter expert who turns document types and business requirements into working, accurate, and governed AI configurations.

Responsibilities

• Configure and deploy document intelligence and document understanding solutions in Azure AI Foundry
  
• Set up projects, model deployments, connections, and access controls
  
• Train, tune, and evaluate custom extraction models for our document types (forms, contracts, invoices, and so on)
  
• Define schemas, field mappings, and confidence thresholds, and measure accuracy against labeled samples
  
• Iterate on prompts, model choices, and configurations to improve extraction quality
  
• Document configurations, evaluation results, and operational runbooks
  
• Work with .NET developers and data engineers to make sure outputs meet integration contracts
  

Required qualifications

• 5+ years of experience with AI/ML platforms, with hands-on Azure AI Foundry and Document Intelligence (or comparable services)
  
• Experience with OCR, layout analysis, and structured extraction from documents
  
• Ability to build labeled datasets and run evaluation cycles
  
• Understanding of responsible AI, security, and governance practices
  
• Strong written communication for configuration documentation
  

Nice to have

• Experience with LLM-based document understanding and prompt engineering
  
• Python scripting for evaluation and automation
  
• Experience in [industry/domain] document types
  

Requirements
Key Responsibilities Develop and maintain enterprise AI applications powered by Anthropic Claude models. Design, build, and optimize inference pipelines for production AI workloads. Integrate Claude APIs into enterprise applications and backend systems. Design and implement Retrieval-Augmented Generation (RAG) solutions using vector databases. Build AI agents and agentic workflows using modern orchestration frameworks. Develop scalable backend services and REST APIs using Python. Implement prompt engineering strategies for different business use cases. Optimize AI application performance for latency, throughput, reliability, and cost. Build reusable AI components, libraries, and integration frameworks. Collaborate with cross-functional teams to translate business requirements into technical solutions. Integrate AI applications with enterprise systems, APIs, and databases. Implement monitoring, logging, evaluation, and observability for AI applications. Troubleshoot production issues and continuously improve platform performance. Follow enterprise security, governance, and responsible AI best practices. Participate in code reviews, technical discussions, and architecture planning. Required Skills & Qualifications 6–8 years of experience in Software Engineering or Backend Development. Minimum 2 years of hands-on experience working with Large Language Models (LLMs) and Generative AI. Strong hands-on experience with Anthropic Claude APIs and enterprise AI integrations. Proficiency in Python. Experience building REST APIs using FastAPI, Flask, or similar frameworks. Strong understanding of: Large Language Models (LLMs) Prompt Engineering Retrieval-Augmented Generation (RAG) AI Agents and Agentic Workflows Embeddings and Semantic Search Experience with AI orchestration frameworks such as: LangChain LangGraph Semantic Kernel Experience working with vector databases such as: Pinecone ChromaDB Weaviate Milvus FAISS Experience integrating AI applications with enterprise platforms and APIs. Good understanding of cloud platforms such as Microsoft Azure or Amazon Web Services (AWS). Familiarity with Git, Docker, Kubernetes, and CI/CD pipelines. Strong analytical, debugging, and problem-solving skills. Excellent communication and collaboration abilities. Preferred Skills Experience building AI copilots or conversational AI solutions. Experience developing multi-agent AI systems. Familiarity with Model Context Protocol (MCP). Experience with Azure AI Foundry or Azure OpenAI Services. Knowledge of AI evaluation and observability tools such as Langfuse, Phoenix, or OpenTelemetry. Exposure to Redis, Kafka, or event-driven architectures. Understanding of AI guardrails, responsible AI, and enterprise security practices. Experience with DevOps and MLOps concepts for AI deployments. Technical Skill Set Programming Languages Python SQL AI & Generative AI Anthropic Claude Prompt Engineering Retrieval-Augmented Generation (RAG) AI Agents LangChain LangGraph Semantic Kernel Backend Technologies FastAPI Flask REST APIs Microservices Databases PostgreSQL Pinecone ChromaDB Weaviate Milvus FAISS Cloud Platforms Microsoft Azure Amazon Web Services (AWS) DevOps & Tools Git Docker Kubernetes CI/CD Pipelines Monitoring & Observability Langfuse OpenTelemetry Phoenix (Preferred) Qualifications Bachelor's degree in Computer Science, Information Technology, Engineering, or a related field. Master's degree is an advantage but not mandatory. Preferred Certifications Azure AI Engineer Associate (AI-102) Azure Fundamentals (AZ-900) AWS Certified Machine Learning – Specialty (Preferred) Anthropic Claude Certification or equivalent Generative AI certification (Preferred)