AI Engineer Level II

Role: AI Engineer – Level II Location: Washington, DC - Onsite Position Summary As an AI Engineer (Level II), you’ll design and implement enterprise-grade AI systems with a focus on Retrieval-Augmented Generation (RAG), agentic AI, and cloud-native ML pipelines. You'll work cross-functionally to operationalize secure, scalable solutions across Azure and AWS platforms, contributing to production-ready, multi-modal GenAI applications. Key Responsibilities AI Architecture & Delivery • Design and deploy RAG pipelines using Azure AI/Search and vector DBs (Redis, FAISS, HNSW). • Develop conversational AI systems with prompt lifecycle management, telemetry, and guardrails. • Integrate LLMs like Azure OpenAI, Llama, Claude, and OSS models across vision and speech domains. Infrastructure & Orchestration • Implement Model Context Protocol (MCP) servers with RBAC, schema versioning, validation, and audit trails. • Deploy Azure AI Agent Service patterns: agent registry, policy enforcement, and telemetry logging. • Use Azure Batch and AWS EMR for parallel inferencing and distributed feature processing. Data Pipeline Engineering • Build and manage ingestion pipelines: document normalization, metadata enrichment, PII redaction, SLA monitoring. • Operate scalable vectorization pipelines with drift detection and quality gates. • Use Azure Data Factory and Databricks; AWS EMR for large-scale Hadoop/Spark workloads. Agentic AI Development • Implement secure tool-calling and multi-agent orchestration using Semantic Kernel, AutoGen, Agent Framework, CrewAI, Agno, and LangChain. • Apply governance, telemetry, and lifecycle management across agent runtimes with MCP controls. Model Ops & Evaluation • Fine-tune and evaluate OSS and proprietary models; conduct A/B tests and latency/cost analysis. • Implement CI/CD pipelines with security scans and validation for AI/LLM workloads. Software Engineering Core • Proficiency in CS fundamentals: algorithms, distributed systems, concurrency, networking. • Experience with SDLC excellence: clean architecture, SOLID, testing pyramids (unit, integration, E2E). • Secure AI app development: input validation, secret hygiene, RBAC, sandboxed functions. • Performance engineering: latency tuning, token optimization, vector index profiling. Cloud AI Tech Stack Azure: Azure OpenAI, AI/Search, AML, AKS, Azure Functions, Key Vault, ADF, Databricks, Azure Batch AWS: SageMaker, Bedrock, Lambda, EMR, Comprehend, API Gateway, S3, EKS Vector DBs: Azure AI Search, Redis, FAISS/HNSW Frameworks: Semantic Kernel, AutoGen, Microsoft Agent Framework, CrewAI, Agno, LangChain Inference: Docker/Ollama, vLLM, GPU provisioning, quantization (GGUF) Qualifications Education: Bachelor’s in CS, Engineering, or equivalent hands-on expertise Experience: 5+ years in software engineering; 2+ years in GenAI/LLM applications (RAG, agents, safety, eval) Certifications (Required) • Microsoft Certified: Azure AI Fundamentals (AI-900) • Microsoft Certified: Azure Data Fundamentals (DP-900) • Responsible AI certifications • AWS Machine Learning Specialty • TensorFlow Developer • Kubernetes CKA or CKAD • SAFe Agile Software Engineering Preferred • Azure AI Engineer Associate (AI-102) • Azure Data Scientist Associate (DP-100) • Azure Solutions Architect (AZ-305) • Azure Developer Associate (AZ-204) Required Skills/Abilities • GenAI architecture mastery: RAG, vector DBs, embeddings, transformer internals, multi-modal pipelines. • Agentic systems: Azure AI Agent Service patterns, MCP servers, registry/broker/governance, secure tool-calling. • Languages: C# and Python (production-grade), .Net, plus TypeScript for service/UI when needed. • Azure & AWS services (see Knowledge Requirements) with hands-on implementation and operations. • Model ops: eval suites, safety tooling, fine-tuning, guardrails, traceability. • Business & delivery: solution architecture, stakeholder alignment, roadmap planning, measurable impact. Desired Skills/Abilities (not Required But a Plus) • LangChain, Hugging Face, MLflow; Kubernetes + GPU scheduling; vector search tuning (HNSW/IVF). • Responsible AI: policy mapping, red-team playbooks, incident response for AI. • Hybrid/multi-cloud deployments using Azure Arc and AWS Outposts; CI/CD for AI workloads across Azure DevOps and AWS CodePipeline. Step into a high-impact role where AI meets cloud scalability. Apply now and bring cutting-edge solutions to life.