AI Developer Standard II

Title: AI Developer Standard II
Duration: 6 Months - Long Term
Location: Washington, DC 20433

Hybrid Onsite: 4 days per week from Day 1, with a full transition to 100% onsite anticipated soon.

Related Domains

• Artificial Intelligence & Machine Learning
• Data & Analytics
• Cloud and Platform Engineering
• Technology Strategy & Sustainability
• Product Development & Digital Solutions

• Assist in implementing Retrieval-Augmented Generation (RAG) pipelines using Azure AI Search and vector database technologies, including document chunking, embedding generation, hybrid retrieval, re-ranking, and citation formatting based on defined architecture.
• Contribute to the development of enterprise conversational AI systems supporting multi-turn interactions, retrieval-grounded responses, prompt lifecycle workflows, guardrails, and telemetry integration under senior guidance.
• Support integration of multiple large language models (LLMs) and modalities (Azure OpenAI, Llama, Claude, and other task-specific models) using routing strategies defined by senior engineers.

• Assist in implementing Model Context Protocol (MCP) based tool interfaces and agent components as defined in system design specifications.
• Develop and maintain tool functions with defined role-based access controls (RBAC), schema validation, versioning, rate limiting, and audit logging under established engineering guidelines.
• Support deployment of Azure AI Agent Service patterns, including agent orchestration workflows, registry integration, governance mechanisms, and telemetry monitoring.
• Assist in executing distributed workloads using Azure Batch and AWS EMR for inferencing, data transformation, and feature processing tasks.

• Contribute to building data ingestion and enrichment pipelines for RAG systems, including document preprocessing, metadata extraction, PII masking, and data quality validation.
• Support vectorization workflows and indexing processes with monitoring for data quality, drift detection, and system reliability.
• Work with Azure Data Factory and Azure Databricks for scalable data processing and assist in AWS EMR-based data engineering tasks.

• Assist in implementing agent-based AI components using frameworks such as Semantic Kernel, AutoGen, Microsoft Agent Framework, CrewAI, LangChain, or similar technologies under senior direction.
• Support configuration and integration of MCP-based controls for agent communication, lifecycle tracking, and monitoring.
• Contribute to debugging and validation of agent workflows in multi-step reasoning systems.

• Assist in evaluation and testing of machine learning and large language models focusing on quality, latency, safety, and cost metrics.
• Support execution of A/B testing, offline evaluation pipelines, and model validation workflows under defined experimental frameworks.
• Participate in CI/CD pipelines for AI systems, including automated testing, security scanning, and deployment validation processes.

• Apply foundational software engineering principles including data structures, algorithms, object-oriented design, and distributed system fundamentals in implementation tasks.
• Follow established SDLC practices including clean coding standards, unit testing, integration testing, and version control workflows.
• Implement secure coding practices including input validation, secrets management, and role-based access control as defined by system requirements.
• Support performance optimization activities such as profiling, caching strategies, vector index tuning, and latency improvements.
• Participate in Agile ceremonies including sprint planning, stand-ups, and collaborative engineering reviews.

• Azure OpenAI Service, Azure AI Search, Azure Machine Learning
• Azure Kubernetes Service (AKS), Azure Functions, API Management
• Key Vault, Event Hub, Application Insights, Log Analytics
• Azure Batch, Azure Data Factory, Azure Databricks

• Amazon SageMaker, AWS Bedrock, Amazon Kendra
• AWS Lambda, API Gateway, Secrets Manager, Amazon S3
• CloudWatch, Amazon EKS, Amazon EMR

• Azure AI Search (vector-based retrieval)
• Redis-based caching systems
• FAISS / HNSW-based vector indexing systems
• Hybrid and semantic search implementations

• Semantic Kernel, AutoGen, Microsoft Agent Framework
• LangChain, CrewAI, Agno

• Docker-based deployments
• vLLM, Triton inference servers
• Basic GPU utilization and quantized model deployment support

• Bachelor s degree in computer science, Engineering, Information Technology, Data Science, or equivalent practical experience.
• Minimum 3 years of software engineering experience, with at least 2 years of exposure to applied AI/ML systems, including RAG pipelines, LLM integration, and model evaluation workflows .

• Microsoft Certified: Azure AI Fundamentals (AI-900)
• Microsoft Certified: Azure Data Fundamentals (DP-900)
• Responsible AI training or certification
• AWS Machine Learning Specialty (or equivalent knowledge)
• TensorFlow Developer certification (or equivalent ML certification)
• Kubernetes CKA/CKAD (or equivalent hands-on experience)
• SAFe Agile Software Engineering certification (or equivalent Agile training)

• Microsoft Certified: Azure AI Engineer Associate (AI-102)
• Microsoft Certified: Azure Data Scientist Associate (DP-100)
• Microsoft Certified: Azure Solutions Architect Expert (AZ-305)
• Microsoft Certified: Azure Developer Associate (AZ-204)

• Understanding of Generative AI systems including RAG, embeddings, transformers, and vector databases
• Exposure to agent-based AI systems and MCP-based architectures under senior guidance
• Programming proficiency in Python and C# for application-level development
• Familiarity with Azure and AWS services used in enterprise AI systems
• Basic understanding of model evaluation, monitoring, and safety concepts
• Ability to work in Agile teams and contribute to implementation of defined engineering tasks

• Exposure to LangChain, Hugging Face, MLflow
• Basic understanding of Kubernetes-based deployments and distributed systems
• Awareness of vector search optimization techniques (HNSW, IVF)
• Understanding of Responsible AI principles and secure AI system design
• Exposure to CI/CD pipelines in Azure DevOps or AWS CodePipeline