Senior Agentic AI Engineer

Opportunity Overview

Responsibilities

• Design, build, and deploy production-grade AI agent applications using self-hosted LLMs and modern agentic frameworks.
• Develop secure, private AI architectures with data isolation, access controls, encryption, and auditability.
• Build agent workflows that integrate enterprise systems, internal applications, and business processes.
• Develop internal tools, user portals, and backend services for AI-powered applications and automation.
• Own deployment, monitoring, versioning, performance optimization, and continuous improvement across the AI lifecycle.
• Implement scalable infrastructure and MLOps practices using Docker, Kubernetes, CI/CD, and cloud or on-premises environments.
• Contribute to commercial AI product development, integration, and optimization.
• Balance performance, scalability, cost, and time-to-market.
• Translate business requirements into technical solutions with product, engineering, and business stakeholders.
• Provide technical leadership, share best practices, and mentor engineers while delivering hands-on work.

Requirements

• 5+ years of AI/ML Engineering experience, ideally in a product-focused or fast-paced technology environment.
• Strong hands-on experience building and deploying production-grade Generative AI and Agentic AI systems.
• Proven experience deploying self-hosted LLMs in private or on-premises environments without external AI API dependency.
• Experience with LLMs such as LLaMA, Mistral, GPT, or Claude and agent frameworks such as LangChain, Semantic Kernel, CrewAI, or MCP architectures.
• Practical experience with RAG, prompt engineering, LLM evaluation, LoRA/QLoRA fine-tuning, and model optimization.
• Strong Python skills and experience building scalable AI workflows, backend services, and production applications.
• Experience with Docker, Kubernetes, CI/CD, MLOps, and AI lifecycle management.
• Strong understanding of authentication, authorization, data isolation, encryption, and audit logging.
• Experience with SQL/NoSQL databases, data modeling, ETL/ELT pipelines, and large-scale datasets.
• Experience deploying and optimizing AI systems across on-premises and cloud environments.
• Strong product ownership, problem-solving, and communication skills.
• A Master's degree in Computer Science, Data Science, or a related technical discipline is preferred.

Technology Environment

• LLMs may include LLaMA, Mistral, GPT, or Claude.
• Agent frameworks may include LangChain, Semantic Kernel, CrewAI, or MCP-based architectures.
• The role uses Python, Docker, Kubernetes, CI/CD, MLOps, SQL/NoSQL databases, and ETL/ELT pipelines.
• AWS exposure is advantageous.