Senior AI Engineer-LLM & Generative AI

501, Fifth Avenue, Suite 805 New York, NY 10017

We are seeking a Senior AI Engineer with practical experience in LLMs, Lang Chain or similar frameworks, and Retrieval-Augmented Generation (RAG) systems. In this role, you will help design and deploy intelligent, secure, and scalable AI solutions that enhance Zscaler’s products and internal automation tools.

The position emphasizes AI backend development and orchestration using Python, cloud deployment (AWS preferred, GCP optional), and integration of LLM-based services with light front-end development for chat interfaces, copilots, and dashboards.

• Solid working experience with Python for AI service development, API integration, and data processing.
• Practical hands‑on experience with Lang Chain, RAG pipelines, or similar developer frameworks.
• Familiarity with LLM integration, prompt design, and embedding‑based retrieval.
• Experience deploying applications on AWS (preferred) or GCP, particularly with EKS, ECS, or Cloud Run.
• Proficiency with Docker, Kubernetes, and cloud‑native service orchestration.
• Experience building RESTful or Graph
  
  QL APIs for AI and data services.
• Understanding of cloud security, scalability, and performance optimisation principles.

• Experience developing conversational UIs, copilots, or AI‑enabled dashboards (e.g., Slack apps, chat widgets).
• Familiarity with React, Next.js, or Type Script for front‑end feature integration.
• Exposure to Hugging Face Transformers, Llama Index, or Lang Graph ecosystems.
• Knowledge of vector databases and data pipeline management.
• Understanding of compliance, privacy, and responsible AI practices in enterprise environments.

• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
• Typically 4–8 years of experience in software or AI engineering, including 2+ years of hands‑on experience with LLMs, Lang Chain, or RAG systems.

• AI Solution Development:
  Build and maintain production‑grade AI systems using LLMs, Lang Chain, and RAG pipelines to solve enterprise‑scale problems.
• Model Integration:
  Implement, fine‑tune, and evaluate LLMs using frameworks such as Lang Chain, Llama Index, Hugging Face, or OpenAI API.
• Backend & API Engineering:
  • Develop scalable Python microservices and APIs for inference and knowledge retrieval.
  • Deploy and operate services on AWS (preferred) or GCP using EKS, ECS, or Cloud Run.
  • Implement observability, monitoring, and autoscaling for production workloads.
• Retrieval‑Augmented Generation (RAG):
  • Design and optimise retrieval workflows using vector databases like FAISS, Pinecone, or Milvus.
  • Integrate both structured and unstructured data into LLM pipelines for grounded responses.
• Front‑End Integration:
  • Collaborate with UI teams to integrate AI experiences into dashboards or chat UIs using React, Next.js, or Type Script.
  • Ensure seamless communication between front‑end components and AI APIs.
• Cloud & Dev Ops:
  • Containerise and deploy using Docker and Kubernetes.
  • Implement CI/CD pipelines with tools like Jenkins, Git Hub Actions, or Terraform.
• Cross‑Functional
  
  Collaboration:
  
  Work closely with product, data science, and platform teams to deliver robust, secure, and impactful AI services.
• Continuous Innovation:
  Stay current with LLM, RAG, and multi‑agent system advancements and drive their adoption across products.

2-11 PM IST