Job Summary
We are seeking a Senior AI Engineer with 6–10 years of experience in artificial intelligence, machine
learning, and generative AI to lead the design and delivery of enterprise-grade AI solutions. The ideal
candidate will have deep expertise in Large Language Models (LLMs), Retrieval-Augmented Generation
(RAG), and AI agent architectures, along with experience deploying scalable AI systems in cloud-native
environments.
In this role, you will architect, build, and scale advanced AI capabilities using modern AI platforms such
as Azure OpenAI, Anthropic, and other LLM services, enabling innovation across SHS R&D digital
platforms. You will also provide technical leadership, mentorship, and architectural guidance to
engineering teams developing AI-powered products and solutions.
Key Responsibilities
AI Solution Architecture
Design and architect enterprise-grade generative AI solutions, including RAG pipelines,
knowledge retrieval systems, and agent-based AI workflows.
Define scalable AI architecture patterns for integrating LLM capabilities into internal platforms
and applications.
Lead the design of AI-driven digital solutions that align with enterprise architecture, security,
and compliance requirements.
LLM & Generative AI Engineering
Lead the development and optimization of LLM-powered applications using technologies such as
Azure OpenAI, Anthropic Claude, and other foundation models.
Architect and implement RAG pipelines, semantic search, vector databases, and knowledgegrounded
AI systems.
Design AI agent orchestration workflows for complex enterprise automation scenarios.
Platform Engineering & Scalability
Build scalable, production-grade AI systems with robust monitoring, evaluation, and
performance optimization.
Implement MLOps/LLMOps practices, including model lifecycle management, prompt
evaluation, observability, and CI/CD integration.
Optimize AI systems for latency, cost, and reliability in production environments.
Technical Leadership
Provide technical leadership and architectural direction for AI initiatives across multiple teams.
Mentor junior AI engineers and data scientists in best practices for LLM engineering, prompt
engineering, and AI system design.
Conduct technical reviews, architecture validations, and design consultations for AI initiatives.
Research & Innovation
Continuously evaluate emerging advancements in Generative AI, NLP, multi-agent systems, and
foundation models.
Drive innovation initiatives, prototypes, and proof-of-concepts to explore new AI capabilities
relevant to R&D workflows.
Identify opportunities to leverage AI for productivity, automation, and knowledge management
across engineering teams.
Skill Requirements
6–10 years of experience in AI/ML engineering, data science, or AI platform development.
Hands-on experience with Generative AI and Large Language Models (LLMs) in production
environments.
Strong experience designing RAG architectures, vector search systems, and AI agents.
Experience building AI-powered applications and services using frameworks such as LangChain,
LlamaIndex, Semantic Kernel, or similar.
Experience deploying AI workloads in cloud environments (Azure, AWS, or GCP).
Experience designing scalable distributed systems and microservice-based architectures.