Job Summary: We are seeking an AI ML Engineer to design, develop, and deploy Generative AI applications, with a focus on Retrieval-Augmented Generation (RAG) and agentic workflows. The ideal candidate will have hands-on experience building applications using LLMs, vector databases, and agent harnesses, along with experience in Azure stack. This role involves developing scalable, production-grade AI solutions that integrate enterprise data with advanced reasoning and automation capabilities.
Responsibilities:
• Design and build agentic applications using Langchain or similar, integrating enterprise data sources (Azure Databricks, documents, APIs)
• Build and optimize RAG vector databases for use by agents using tools like Azure AI Search, or similar
• Integrate LLMs (Azure OpenAI, GPT models) into enterprise applications with proper prompt engineering and optimization
• Implement evaluation, monitoring, and guardrails for AI systems (accuracy, bias, hallucination control)
• Collaborate with data engineers and application teams to integrate AI solutions into production systems
• Optimize application performance, latency, and cost for large-scale deployments
• Communicate insights clearly to both technical and non-technical stakeholders
Minimum Qualifications
• 5+ years of experience in AI/ML Engineering, Data Science, or related field
• Experience using data from Azure Databricks or similar relational databases
• Strong hands-on experience with Python (core development language), Git, Github; LLM frameworks especially Langchain; RAG architectures and vector search concepts
• Experience with Azure AI ecosystem, including Azure OpenAI models and Azure AI Search
• Understanding of AI ML concepts, LLMs, vector databases, RAG, agents
• Familiarity with APIs, microservices, MCP and scalable system design
• Strong communication skills