Job Description
Key Responsibilities
The Role
The AI Engineer is responsible for building and scaling enterprise-grade Generative AI platforms that enable rapid development and deployment of LLM-powered applications across the organization. This role focuses on developing reusable GenAI infrastructure including RAG pipelines, vector databases, model serving layers, and agent orchestration frameworks.
Key Responsibilities
GenAI Platform Development
- Build and maintain RAG pipelines and LLM orchestration frameworks
- Develop reusable GenAI services and APIs
- Enable multi-agent and agentic workflows
Infrastructure & Systems
- Implement scalable model serving infrastructure (vLLM, Triton, APIs)
- Manage vector databases and embedding pipelines
- Optimize performance and cost of LLM systems
Platform Enablement
- Provide reusable building blocks for AI teams
- Enable rapid experimentation and deployment
- Collaborate with AI/ML teams to accelerate GenAI adoption
Innovation
- Evaluate emerging GenAI tools and frameworks
- Drive adoption of best practices in LLMOps
Key Requirements
- Bachelor/ MSc / PhD in Computer Science, Mathematics or related field of study
- Ongoing commitment to training and professional development in AIML, Aviation Domain, Cargo handling, Ground Handling milestones, Ground Freight and Food Solutions.
- 3 to 5 years in AI engineering / backend systems
- Strong expertise in: LLMs, RAG, embeddings, LangChain / LlamaIndex, CrewAI, Vector DBs (FAISS, Pinecone)