Description

You will design, orchestrate, and deploy end-to-end Generative AI and Large Language Model (LLM) solutions for complex enterprise use cases.

This role is on-site.

Responsibilities

• Architect LLM workflows including prompt orchestration, Retrieval-Augmented Generation (RAG), vector store integration, and real-time inference pipelines.
• Design conversational systems, semantic search, and summarization tools using OpenAI, Claude, and Gemini.
• Implement data governance and lineage using Databricks Unity Catalog to manage metadata, access controls, and audit trails for AI datasets.
• Integrate feedback loop systems, such as RLHF and user signal-driven reinforcement, to refine model performance.
• Optimize model latency, cost, and performance through fine-tuning, prompt engineering, and token management.

Required Skills

• 7+ years in AI/ML solution architecture, with 2+ years focused on LLMs and Generative AI.
• Hands-on experience with OpenAI (GPT-4/o), Claude, and Gemini API integration.
• Proficiency in Databricks, including Unity Catalog, Delta Lake, and MLflow.
• Experience with LLM orchestration tools like LangChain or LlamaIndex and vector databases such as FAISS, Weaviate, or Pinecone.
• Strong Python development skills for building REST APIs and orchestration pipelines.
• Deep understanding of data governance, metadata management, and lineage in large-scale environments.
• Experience deploying models across AWS, Azure, or GCP.

Preferred Skills

• Experience fine-tuning open-source models like LLaMA or Mistral using LoRA/QLoRA.
• Knowledge of HIPAA, GDPR, or SOC2 compliance requirements in AI systems.

Key Skills

Education

Any Gradute