Gen AI Engineer
Job Description
• Develop and implement AI/ML solutions using Python and key ML libraries such as PyTorch, scikit-learn, and Hugging Face
• Design, build, and deploy GenAI and LLM-based applications including RAG systems, chat assistants, copilots, content generation, summarization, and workflow automation
• Work with agent frameworks (LangGraph, Semantic Kernel, LangChain, AutoGen, CrewAI, OpenAI Assistants) and integrate external tools
• Deploy and manage solutions on cloud GenAI stacks like Azure OpenAI / Azure AI Studio, AWS Bedrock, or Google Vertex AI, including vector search implementation
• Implement evaluation and safety guardrails, including jailbreak/prompt-injection mitigation, PII redaction, and compliance-focused design
• Build enterprise copilots or assistants integrated with business systems such as ticketing, CRM/ERP, data lakes, and search
• Apply routing, mixture-of-models, and cost-aware policy design for efficient LLM usage
• Design dashboards and perform operational/product analytics using tools like Power BI or Superset