Mid-Level AI Platform Engineer

Responsibilities

• Develop and implement GenAI applications leveraging Large Language Models (LLMs)
• Retrieval-Augmented Generation (RAG) architectures
• Prompt engineering techniques
• Agentic AI concepts and workflows
• Build intelligent pipelines using frameworks such as Lang Chain, Lang Graph, and Microsoft Foundry Agent Service
• Evaluate solution performance, accuracy, and scalability of GenAI implementations
• Contribute to the end-to-end GenAI lifecycle, including Solution design and development
• Integration and deployment
• Performance tuning and optimization
• Support secure deployment, horizontal scaling, and operational stability of GenAI workloads
• Assist in implementing monitoring, logging, and observability practices for production environments
• Develop and deploy GenAI systems across cloud platforms (Azure and AWS)
• Contribute to distributed system design for scalable AI workloads
• Utilize modern infrastructure practices:
  Containerization (Docker)
• Orchestration (Kubernetes)
• Infrastructure as Code (Terraform, ARM/Bicep)

• Bachelor’s degree in Computer Science, Engineering, or related field
• 5–8 years of experience in software or platform engineering
• 2+ years hands‑on experience with GenAI systems, including LLMs and RAG architectures and vector databases
• Understanding of agentic AI concepts and exposure to frameworks such as Lang Chain or Lang Graph
• Experience with cloud platforms (Azure and/or AWS)
• Knowledge of distributed systems and scalable application design
• Proficiency in Python development
• Experience with Docker, Kubernetes, and Infrastructure as Code tools
• Experience deploying GenAI or ML solutions in production environments
• Familiarity with observability and monitoring tools
• Understanding of AI governance, compliance, and security practices
• Experience in financial services or other regulated industries is a plus