AI/ML Engineer – LLM & RAG Systems
About the Role
A high-impact AI engineering initiative is seeking professionals with strong experience in large language models, retrieval-augmented generation, and scalable machine learning infrastructure. The environment focuses on production-grade AI systems, secure cloud deployment, and advanced orchestration workflows supporting enterprise and regulated use cases.
This opportunity is ideal for individuals who thrive in technically demanding environments, enjoy building AI systems end-to-end, and can collaborate across engineering, security, and product functions. Candidates with experience in agentic AI frameworks and modern cloud ecosystems will be well aligned with the role.
The work involves designing and deploying AI applications powered by LLMs, building orchestration pipelines, integrating APIs and SDKs, and maintaining reliable data systems where scalability, security, and operational reliability are critical.
What You'll Do
- Design and optimize AI/ML systems using LLMs, RAG architectures, and prompt engineering techniques
- Develop multi-agent workflows using orchestration frameworks such as LangGraph and LangChain
- Deploy AI solutions within secure cloud environments including AWS, Azure, and Google Cloud platforms
- Build and maintain ETL pipelines, metadata systems, and structured data workflows for AI operations
- Develop REST APIs and SDK integrations to support model interaction and platform interoperability
- Implement CI/CD workflows and apply secure coding standards across deployment pipelines
- Collaborate with engineering, product, and security stakeholders to deliver scalable AI infrastructure
- Document architectural decisions, workflows, and implementation details for technical and operational teams
Requirements
- Strong proficiency in Python for AI/ML development
- Hands-on experience with LLM applications and RAG-based systems in production environments
- Experience with prompt engineering and agentic AI workflows
- Familiarity with LangChain, LangGraph, or similar orchestration frameworks
- Knowledge of AWS, Azure, or Google Cloud AI services and deployment workflows
- Experience building APIs, SDK integrations, and scalable backend services
- Understanding of ETL processes, data pipelines, metadata management, and ontology structures
- Experience implementing CI/CD pipelines and secure development practices
- Strong written and verbal communication skills
- Ability to work effectively in cross-functional technical environments
- Preferred: Experience with enterprise AI platforms such as OpenAI Enterprise, Gemini Enterprise, Anthropic, or similar ecosystems
- Preferred: Exposure to regulated or government-grade cloud environments and compliance requirements
- Preferred: Familiarity with advanced API architecture and metadata catalog systems such as MCP