About ZS

ZS is a management consulting and technology firm focused on transforming global healthcare and beyond. Our most valuable asset is our people. At ZS, you will work alongside a diverse team of experts, innovators, and problem-solvers who are passionate about creating impactful solutions for patients, caregivers, consumers, and businesses worldwide.

We partner closely with our clients to develop custom strategies, analytics solutions, and technology products that drive meaningful business outcomes. If you are curious, innovative, and passionate about leveraging cutting-edge AI technologies to solve complex problems, ZS offers an setting where you can thrive and make a lasting impact.

At ZS, we celebrate diversity, equity, and inclusion. We believe that our varied backgrounds, experiences, and perspectives fuel innovation and help us build stronger solutions for our clients and communities.

About the Role

The ZS India Capability & Expertise Center (CEC) houses more than 60% of ZS professionals across offices in New Delhi, Pune, and Bengaluru. Our teams collaborate with colleagues across North America, Europe, and East Asia to deliver innovative solutions for global clients.

As a Senior LLM Engineer, you will be part of ZS's Scaled AI Practice, working at the forefront of Generative AI innovation. You will design, develop, and deploy enterprise-grade GenAI applications while collaborating with data scientists, ML engineers, and product teams to solve high-value business problems using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and modern AI infrastructure.

Key Responsibilities

- Design and develop enterprise-scale Generative AI applications such as:





- Question Answering Systems
- AI Search and Retrieval Engines
- Information Extraction Solutions
- Content Generation and Authoring Platforms

- Build and optimize Retrieval-Augmented Generation (RAG) pipelines using frameworks such as:

- LangChain
- LlamaIndex

- Work with Large Language Models including:

- Azure OpenAI
- OpenAI Models
- GPT-based architectures

- Engineer, evaluate, and optimize prompts using techniques such as:

- Zero-shot prompting
- Few-shot prompting
- Contextual prompting
- Chain-of-thought methodologies

- Design and implement GenAI application architecture including:

- Vector Databases
- Embedding Models
- Chunking Strategies
- Caching Layers
- Retrieval Systems

- Develop scalable, secure, and production-grade AI solutions capable of supporting:

- Large user bases
- High-volume datasets
- Low-latency response requirements

- Collaborate with Data Science, Engineering, Product, and Business teams to translate business requirements into AI-driven solutions.

- Contribute to AI platform development, deployment automation, and best practices across the complete AI/ML lifecycle.

Required Skills & Qualifications

Technical Skills

- Solid proficiency in Python.

- Experience developing Generative AI applications using:

- Azure OpenAI
- LangChain




- LlamaIndex
- Vector Databases

- Experience with cloud platforms:

- Azure (preferred)
- AWS
- GCP

- Strong understanding of:

- Data Structures
- Software Engineering Principles
- System Design
- Distributed Computing

- Experience designing and deploying solutions on cloud-based and distributed computing platforms.

- Hands-on experience with:

- Retrieval-Augmented Generation (RAG)
- Embeddings
- Prompt Engineering
- LLM Evaluation Frameworks

- Knowledge of Machine Learning and Data Science fundamentals.

Good to Have

- Experience with:

- Kubernetes
- Docker
- CI/CD Pipelines
- DevOps Practices

- Experience building and scaling enterprise AI products.

- Familiarity with MLOps or LLMOps practices.

- Experience monitoring, evaluating, and optimizing production AI systems.

Preferred Qualifications

- Bachelor's or Master's degree in Computer Science, Engineering, Data Science, Artificial Intelligence, or related field.

- Demonstrated experience building production-grade AI/ML applications.

- Strong analytical and problem-solving skills.

- Ability to learn new technologies quickly and innovate in a rapid-paced environment.

- Excellent communication and stakeholder management skills.

Why Join ZS?

- Work on cutting-edge Generative AI and LLM initiatives.
- Build solutions used by global Fortune 500 clients.
- Collaborate with world-class AI, Data Science, and Engineering teams.
- Accelerate your career in one of the industry's most advanced AI ecosystems.
- Thrive in a culture that values innovation, learning, diversity, and impact.

📌 LLM Engineer (Pune)
🏢 ZS
📍 Pune