Job Overview
We are looking for an innovative and hands-on AI Engineer to design, build, and optimize next-generation AI solutions focused on Agentic AI systems and Retrieval-Augmented Generation (RAG) architectures. The ideal candidate will have strong experience in building intelligent applications using modern AI frameworks, vector databases, and cloud-based AI platforms—preferably within Microsoft Azure ecosystem tools such as Azure AI Foundry and related SDKs.
You will work closely with product, engineering, and data teams to develop scalable AI agents, deploy production-grade GenAI applications, and monitor model performance through robust AI telemetry and observability practices.
Key Responsibilities
- Design and develop Agentic AI applications using modern agent frameworks (e.g., LangChain, LlamaIndex, AutoGen, Semantic Kernel).
- Build and optimize RAG (Retrieval-Augmented Generation) pipelines including:
- Document ingestion and chunking
- Embedding generation
- Vector database design and management
- Retrieval optimization and prompt orchestration
- Create and manage vector stores/databases such as Azure AI Search, Pinecone, Weaviate, or Chroma.
Develop AI solutions using Azure AI Services, including:
- Azure OpenAI Service
- Azure AI Foundry
- Azure Machine Learning
- Azure AI Search
- Utilize Foundry SDKs and APIs to build, test, and deploy enterprise AI solutions.
- Implement AI telemetry and observability using tools such as Azure Monitor, Application Insights, LangSmith, or OpenTelemetry.
- Monitor model performance, latency, hallucinations, prompt quality, and system reliability.
- Collaborate with engineering teams to deploy secure, scalable, and production-ready AI solutions.
Required Skills & Qualifications
- 3+ years of experience in AI/ML Engineering, GenAI, or LLM application development
- Strong experience with Agentic AI frameworks
- Hands-on experience building RAG systems and vector databases
- Experience with Azure AI Services and cloud-native AI deployments
- Experience using Azure AI Foundry / Foundry SDKs
- Strong understanding of AI telemetry, observability, and model monitoring
- Proficiency in Python
- Experience with APIs, prompt engineering, and LLM orchestration
- Familiarity with Docker, CI/CD, and cloud deployment practices
Nice to Have
- Experience with multi-agent workflows
- Knowledge of fine-tuning and model evaluation
- Experience with Kubernetes and MLOps pipelines
- Exposure to responsible AI and AI governance frameworks
