Zensar Technologies - Generative AI Application Developer - LLM/RAG

Position : Generative AI Application Developer

Experience : 7-16 years

Location : Bangalore, Hyderabad, and Pune, India

Notice Period : Early joiners are highly appreciated.

Job Summary :

We are seeking a highly skilled and experienced Generative AI Application Developer to architect, develop, and deploy production-grade AI systems. The ideal candidate will possess deep technical expertise in the end-to-end lifecycle of Generative AI models, with a strong focus on building scalable and robust applications. This role requires a hands-on developer who can translate complex business challenges into innovative solutions using Large Language Models (LLMs) and other generative technologies.

Key Responsibilities :

Model Development & Fine-Tuning :

- Implement and fine-tune Large Language Models (LLMs) using custom datasets to meet specific business requirements.

- Apply techniques such as Retrieval-Augmented Generation (RAG) and prompt engineering to enhance model performance and reduce hallucinations.

Data Engineering & Preparation :

- Manage and optimize vector databases for efficient semantic search and information retrieval.

Application Development & Integration :

- Build prototypes and demonstrate proof-of-concepts (POCs) to technical and business stakeholders.

- Ensure seamless integration of AI applications with existing enterprise systems.

Deployment & MLOps :

- Implement CI/CD pipelines for continuous integration and deployment of machine learning code.

- Monitor model performance, latency, and resource utilization post-deployment.

Research & Innovation :

- Evaluate and experiment with new models, frameworks, and tools to drive innovation.

Required Skills :

Programming :

- Expert-level proficiency in Python.

- Strong experience with software engineering fundamentals, including object-oriented programming, data structures, and algorithms.

ML/AI Expertise :

- Deep understanding of deep learning frameworks such as PyTorch or TensorFlow.

- Hands-on experience with Generative AI models (e.g., GANs, VAEs) and architectures (e.g., Transformers, diffusion models).

- Proven experience with Large Language Models (LLMs), fine-tuning, RAG, and prompt engineering.

MLOps & Cloud :

- Familiarity with MLOps tools like MLflow, Kubeflow, or DVC.

- Experience with containerization technologies like Docker.

Databases & APIs :

- Proficient in SQL and knowledge of NoSQL databases.

- Experience with building and consuming RESTful APIs and microservices.

Libraries :

Software Engineering Practices :

Preferred Skills :

- Knowledge of specific cloud-native services like AWS Bedrock, Azure OpenAI Service, or GCP's Vertex AI Model Garden.

- Familiarity with other programming languages such as Java or C++ for high-performance computing.

- Experience with UI/UX frameworks (React, Angular) to build user interfaces for AI applications.

- Contributions to open-source projects in the AI or machine learning community.

- Relevant cloud certifications (AWS Certified Machine Learning Specialty).