Database/Compute -Sr. Engineer
Core
Design and develop end-to-end Generative AI solutions using LLMs, build and optimize RAG pipelines utilizing vector databases, and implement prompt engineering and agentic workflows.
Role type
Generative AI Engineer (LLM & RAG)
Builds
Scalable, secure, and production-ready Generative AI solutions and RAG-based AI assistants.
Domain
Generative AI, Large Language Models, Vector Databases, Cloud Infrastructure
Deliverable
production ML models
Required skills
Python, SQL, Machine Learning, Deep Learning, Generative AI, LLMs, RAG Architecture, LangChain, LangGraph, LlamaIndex, Vector Databases, AWS Bedrock, SageMaker, Lambda, ECS/EKS, MLOps, CI/CD, REST APIs, Microservices
Preferred skills
Ansible, Azure Repos, GitHub, ServiceNow, Linux automation, AI assistants/copilots
Technologies
LangChain, LangGraph, LlamaIndex, OpenSearch, Pinecone, Chroma DB, FAISS, AWS Bedrock, SageMaker, Lambda, ECS, EKS
Responsibilities
Design and develop end-to-end Generative AI solutions using LLMs. Build and optimize RAG pipelines utilizing vector databases and enterprise knowledge sources. Fine-tune, evaluate, and deploy foundation models for domain-specific use cases. Develop scalable data pipelines for ingestion, transformation, embedding generation, and retrieval. Implement prompt engineering, agentic workflows, and AI orchestration frameworks.
Seniority
Senior, hands-on IC