Staff Engineer, Generative AI Engineer

Accountabilities:

• • Design, develop, and deploy enterprise-grade Generative AI, Agentic AI, AI agent, and conversational AI solutions using Python and FastAPI.
  • Architect and implement multi-agent systems, including workflows, reasoning, memory, tool integrations, orchestration, and agent coordination.
  • Design and optimize scalable RAG pipelines, covering document processing, chunking, embeddings, vector search, retrieval, grounding, and response generation.
  • Develop and refine LLM prompts, retrieval strategies, agent workflows, and AI responses to maximize accuracy, reliability, relevance, and business value.
  • Integrate AI agents with enterprise applications through REST APIs, MCP, and A2A protocols.
  • Build secure, scalable cloud-native AI applications using technologies such as OAuth2/JWT, Key Vault, Responsible AI guardrails, and governance controls.
  • Develop and maintain CI/CD and GitOps pipelines using Azure DevOps, Docker, Kubernetes, Argo CD, and related technologies.
  • Establish robust approaches to testing, AI evaluation, observability, monitoring, logging, and distributed tracing, leveraging tools such as LangSmith, OpenTelemetry, and Elasticsearch.
  • Optimize AI applications for performance, scalability, reliability, latency, cost efficiency, and production readiness.
  • Identify and address security, governance, and operational risks associated with enterprise AI applications.
  • Collaborate with business, engineering, platform, security, and cloud teams to translate business requirements into scalable AI solutions.
  • Evaluate emerging LLMs, agentic AI frameworks, AI engineering platforms, and industry practices, recommending technologies that can improve the AI ecosystem.
  • Provide technical leadership and mentor engineers on GenAI, LLM applications, RAG architectures, agent design, and production AI engineering.

  Requirements:

  • 5.5+ years of professional experience, including strong and recent hands-on experience in AI/Generative AI engineering.
  • Bachelor’s or master’s degree in Computer Science, Information Technology, or a related technical field.
  • Strong hands-on expertise in Python and production-grade AI/GenAI application development.
  • Proven experience with FastAPI for building scalable, secure, and production-ready APIs.
  • Strong knowledge of LLMs, prompt engineering, RAG, embeddings, vector databases, and retrieval optimization.
  • Hands-on experience designing and implementing enterprise AI agents, conversational AI, and Agentic AI solutions.
  • Experience with agent orchestration frameworks such as LangGraph, CrewAI, Temporal, or comparable technologies.
  • Experience integrating AI agents with enterprise systems through REST APIs, MCP, and A2A protocols.
  • Familiarity with enterprise LLM platforms such as Azure OpenAI and AWS Bedrock.
  • Experience with Docker, Kubernetes, CI/CD, Azure DevOps, Argo CD, and GitOps practices.
  • Strong understanding of AI security, OAuth2/JWT, Responsible AI guardrails, governance, and enterprise application security.
  • Experience implementing AI evaluation, observability, monitoring, logging, and tracing, preferably using tools such as LangSmith, OpenTelemetry, or Elasticsearch.
  • Good-to-have experience with Semantic Kernel, AWS Bedrock AgentCore, and enterprise AI governance.
  • Strong analytical and problem-solving skills, with the ability to work through complex technical challenges.
  • Excellent stakeholder management, communication, collaboration, and technical leadership abilities.
  • Demonstrated ability to mentor engineers and influence architecture and engineering practices across teams.

  Benefits:

  • Opportunity to work on cutting-edge Generative AI and Agentic AI solutions with enterprise-scale applications.
  • Exposure to modern technologies spanning LLMs, RAG, multi-agent architectures, vector databases, cloud platforms, and AI orchestration.
  • Opportunity to take a Staff-level technical leadership role, influencing architecture and engineering standards.
  • Collaboration with multidisciplinary teams across engineering, cloud, security, platform, and business functions.
  • Dynamic, global, and non-hierarchical work environment.
  • Opportunities to mentor engineers and contribute to the development of advanced AI engineering capabilities.
  • Continuous exposure to emerging AI technologies, frameworks, and industry best practices.
  • Professional growth opportunities within a large, globally distributed technology organization.
  • Competitive compensation and benefits, subject to the applicable employment package and local policies.