Location : Bangalore - Zeiss Office

Job Title : GenAI Engineer (LLM Applications)

Company : Carl Zeiss India Pvt Ltd

About the Role :

We are looking for an enthusiastic and motivated AI Engineer to join our team. In this role, will contribute to the design and implementation of production-grade applications powered by Large Language Models (LLMs). You will be a key player in building next-generation agentic workflows, Patient assistance(chatbots) and RAG-based systems, learning and applying excellent coding practices to help solve complex business challenges.

Responsibilities :

- Assist in designing, developing, and deploying end-to-end, production-grade LLM-powered applications along with the team members.

- Help build and maintain stateful, multi-step AI applications and agentic workflows using modern frameworks such as LangChain and LangGraph.

- Contribute to the implementation of Retrieval-Augmented Generation (RAG) pipelines to ground LLMs in external data.

- Participate in the lifecycle of data ingestion, chunking, embedding, and indexing for vector databases to support robust RAG systems.

- Help evaluate and optimize the performance and output quality of LLM applications, focusing on metrics like

relevance, factuality, and safety.

- Collaborate with cross functional teams and other engineers to understand requirements and carryout the development.

- Proactively learn and apply the latest advancements in LLM technology, including agentic frameworks and advanced RAG techniques.

- Follow and contribute to best practices and development standards for building scalable, reliable, and maintainable LLM-powered applications.

- Write clean, maintainable, and well-documented code, adhering to team-wide coding standards and best practices for production-level software.

- Assist in diagnosing and resolving technical issues related to our LLM-powered applications and infrastructure.

Qualifications :

- Bachelor's or Masters degree in computer science, Engineering, or a related field (or equivalent practical experience).

- 3-4 years of hands-on LLM and GenAI software development experience, with an interest or experience in building LLM-powered applications.

- Strong proficiency in Python and a good understanding of building scalable software.

- Atleast 2 years of Experience with prompt engineering, including techniques for crafting and testing prompts to elicit desired behaviors from various LLMs.

- Familiarity with implementing LLM patterns like Retrieval-Augmented Generation (RAG) and an understanding of the underlying components.

- Demonstrated ability to learn quickly, work collaboratively, and deliver high-quality code.

- Good analytical and problem-solving skills with an eagerness to tackle complex technical challenges.

- Strong communication skills.

Preferred Qualifications :

- Hands-on experience with LLM application frameworks (e.g., LangChain, LangGraph, LlamaIndex).

- Practical experience with vector databases (e.g., Pinecone, Weaviate, Chroma, FAISS) and embedding models.

- A portfolio of completed software projects (including personal or academic) that demonstrates your technical skills and coding practices.

- Familiarity with deploying applications on a major cloud platform (AWS, Azure, or GCP).

- Experience with version control systems (e.g., Git) and CI/CD concepts.