AI Engineer

Oakwood Systems Group Inc. is seeking a hands-on, experienced AI Engineer to design, build, and deploy secure, production-ready AI applications, copilots, and agents on the Microsoft cloud. The role emphasizes generative AI delivery, retrieval-augmented generation (RAG), agentic workflows, enterprise integration, and measurable production evaluation.

Responsibilities

• Design, build, and deploy production AI applications, copilots, and agents using Microsoft Azure and modern AI frameworks.
• Build RAG and enterprise knowledge solutions using embeddings, vector search, document processing, metadata, and retrieval strategies that support grounded, source-aware answers.
• Design agentic workflows that use tools, APIs, structured outputs, memory or state, human approval, and multi-step orchestration to automate business processes safely.
• Integrate AI capabilities with enterprise systems and data sources through REST APIs, Microsoft Graph, Power Platform, databases, SaaS platforms, and custom services.
• Develop maintainable backend services and APIs, primarily in Python, with testing, error handling, logging, security, and performance considerations.
• Implement evaluation approaches for AI quality, groundedness, reliability, safety, latency, and cost, using results to improve prompts, retrieval, orchestration, and model selection.
• Apply production engineering practices including source control, automated testing, CI/CD, containerization, secrets management, observability, and environment promotion.
• Apply enterprise security and governance practices, including identity, role-based access, data boundaries, auditability, responsible AI controls, and human-in-the-loop patterns where appropriate.
• Collaborate with client business and technical stakeholders to understand workflows, clarify requirements, prototype solutions, explain tradeoffs, and translate AI goals into deployable designs.
• Contribute to architecture reviews, code reviews, estimation, technical discovery, and solution design for new client opportunities.
• Create reusable patterns, accelerators, reference implementations, and delivery assets to improve consistency across future Oakwood AI engagements.
• Document solutions clearly and support knowledge transfer so client teams can operate and extend delivered systems.
• Mentor less-experienced engineers and help establish pragmatic engineering standards for production AI delivery.

Requirements

• 5+ years of professional engineering experience in software engineering, machine learning engineering, data engineering, applied AI, backend development, or a related discipline, with meaningful ownership of production systems.
• 2+ years building generative AI / LLM-powered applications or AI-enabled software, including at least one solution taken beyond prototype into a production or production-like environment.
• Strong Python skills and experience building production services, APIs, integrations, or data and AI pipelines.
• Hands-on experience with LLM application patterns including prompt design, RAG, embeddings, vector search, structured outputs, function or tool calling, and agent orchestration.
• Experience evaluating AI systems using measurable criteria (quality, reliability, safety, latency and/or cost) rather than subjective demos alone.
• Experience with cloud-based applications and AI services, with strong Azure experience preferred and ability to work effectively in a Microsoft-centric environment.
• Working knowledge of SQL and enterprise data integration, including reasoning about data quality, access, lineage, and data architecture impacts on AI outcomes.
• Experience with modern engineering practices including Git, peer review, automated testing, CI/CD, containers, APIs, logging and monitoring, and secure configuration and secrets management.
• Ability to troubleshoot production AI behavior such as retrieval failures, hallucinations, tool-calling errors, prompt regressions, latency, cost, and unexpected edge cases.
• Strong client-facing communication skills to explain technical concepts, architecture decisions, risks, and tradeoffs to engineers and business stakeholders.
• Ability to work independently in a consulting environment, manage competing priorities, and move from incomplete requirements to a structured implementation plan.
• Bachelor’s degree in Computer Science, Engineering, Data Science, Mathematics, or a related field, or equivalent practical experience.

Technologies

• Microsoft Azure
• Python
• REST APIs
• Microsoft Graph
• Power Platform
• SQL
• Git, CI/CD, containers
• Microsoft Foundry, Azure AI Foundry, Azure OpenAI, Azure AI Search
• Copilot Studio, Power Automate
• Semantic Kernel, LangGraph, AutoGen, LangChain, CrewAI
• Model Context Protocol (MCP)
• Azure Functions, Container Apps, App Service, AKS, API Management
• Cosmos DB, Azure SQL, Key Vault, Entra ID
• Microsoft Fabric, Databricks
• GitHub Copilot, Claude Code, Codex, Cursor

Preferred Qualifications

• Hands-on experience with Microsoft Foundry / Azure AI Foundry, Azure OpenAI, Azure AI Search, Copilot Studio, Power Automate, or related Microsoft AI services.
• Experience with one or more orchestration frameworks such as Semantic Kernel, LangGraph, AutoGen, LangChain, CrewAI, or custom agent frameworks.
• Experience with Model Context Protocol (MCP), agent-to-tool integration patterns, or reusable enterprise tool registries.
• Experience with Azure application services including Functions, Container Apps, App Service, AKS, API Management, Cosmos DB, Azure SQL, Key Vault, and Entra ID.
• Experience with MLOps / LLMOps practices including evaluation pipelines, model or prompt versioning, tracing, monitoring, feedback loops, and production incident response.
• Experience with Microsoft Fabric, Databricks, or other modern data platforms used to prepare governed enterprise data for AI.
• Experience with classical machine learning, NLP, deep learning, fine-tuning, multimodal models, or model serving where the use case requires more than foundation-model APIs.
• Experience using AI-assisted development tools such as GitHub Copilot, Claude Code, Codex, or Cursor while applying disciplined engineering review for correctness, security, and maintainability.
• Prior consulting, professional services, systems integration, or Microsoft partner experience.
• Relevant Microsoft or cloud certifications such as Azure AI Engineer, Azure Developer, Azure Solutions Architect, or equivalent.

What Success Look Like

• AI solutions move from discovery and prototype to secure, supportable production deployments with clear acceptance criteria.
• Clients can articulate the business value of delivered systems, not only technical capability.
• AI quality improves through repeatable evaluation, observability, and feedback rather than one-time demonstrations.
• Solutions integrate cleanly with client applications, data, identity, and operating processes and remain maintainable after handoff.
• Reusable engineering patterns and delivery assets reduce effort and risk across future engagements.
• Clients and teammates view the engineer as a trusted delivery partner combining technical depth, sound judgment, and practical execution.