AI/ML Engineer (Generative AI & LLMs)

Role overview

AI/ML Engineer (Generative AI & LLMs) at Tudip Technologies

AI / ML Development: Design and build AI-powered applications using transformer-based Large Language Models (LLMs) .

The ideal candidate will have strong experience with transformer-based Models, LLM engineering, scalable backend systems, and cloud-based AI infrastructure.

Responsibilities

• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines for context-aware AI systems.
• Implement prompt engineering techniques to improve LLM accuracy and performance.
• Apply techniques to reduce hallucinations and improve model reliability .
• LLM Engineering: Build end-to-end LLM pipelines using Lang Chain or Llama Index .
• Integrate vector databases for semantic search and contextual retrieval .
• Develop AI workflows involving multiple model interactions and tool integrations .
• Contribute to improving LLM evaluation and monitoring frameworks .
• Backend & Platform Development: Develop scalable Python-based backend services for AI applications.
• Design and implement REST APIs for AI-driven systems.
• Build systems using microservices architecture and distributed systems principles .
• Data Infrastructure & Scalability: Implement scalable pipelines using Redis, message queues (Pub/Sub or Kafka) , and caching mechanisms.
• Architect backend systems capable of handling large-scale user traffic and AI workloads .
• Ensure system performance, reliability, and efficient resource utilization.
• Cloud & Deployment: Deploy and manage AI systems on Google Cloud Platform (preferred) or AWS/Azure .
• Work with cloud-native infrastructure for model deployment, scaling, and monitoring .
• Collaboration: Collaborate with product managers, data scientists, and engineering teams to translate business requirements into AI solutions.
• Participate in architecture discussions and technical decision-making .
• Continuously explore and adopt latest advancements in AI and Generative AI technologies .

Required qualifications

• Bachelor’s or Master’s degree in: Computer Science Artificial Intelligence.
• Machine Learning.
• Data Science. or equivalent practical experience in AI/ML engineering.
• 2+ years of experience working with AI/ML or LLM-based systems .
• AI / Machine Learning: Strong understanding of Transformer architecture .
• Experience working with Large Language Models (LLMs) .
• Knowledge of RNNs, LSTMs, and the evolution toward transformer-based architectures .
• Understanding of Reinforcement Learning from Human Feedback (RLHF) .
• LLM Engineering: Prompt engineering.
• Retrieval-Augmented Generation (RAG) pipelines.
• Experience with Lang Chain or Llama Index .
• Experience working with vector databases .
• Backend & Systems: Python programming .
• Building REST APIs .
• Microservices architecture.
• Distributed systems design.
• Data & Infrastructure: Redis.
• Message queues such as Google Pub/Sub or Kafka .
• Designing scalable backend systems .
• Experience with AWS or Azure also acceptable.
• Knowledge of test automation frameworks .
• Experience with LLM evaluation frameworks .
• Familiarity with MLOps pipelines and model lifecycle management.
• Employer experience: 2 years

Preferred qualifications and skills

• Cloud Platforms: Google Cloud Platform (preferred) .
• Good to Have Experience building AI developer tools or AI platforms .

Employment details

• Location: India

Additional role details

• AI/ML Engineer (Generative AI & LLMs)
• The ideal candidate will have strong experience with transformer-based models, LLM engineering, scalable backend systems, and cloud-based AI infrastructure