Junior Generative AI And Large Language Models Integration Engineer

What role will you play in the team

As a Junior Generative AI and Large Language Models Integration Engineer, you will play a critical role in architecting cutting-edge conversational interfaces, deploying foundational models, and embedding advanced natural language processing capabilities into enterprise data workflows. Your core focus will revolve around building scalable retrieval-augmented generation pipelines, fine-tuning pre-trained transformer architectures, and ensuring seamless API connectivity across decentralized cloud infrastructure to transform unstructured enterprise data into actionable insights and automated decision-making engines.

What you will do

You will design, develop, and deploy production-grade Large Language Model applications leveraging OpenAI API, Claude API, and local open-source frameworks. Your daily activities will include building robust Retrieval-Augmented Generation (RAG) pipelines, managing vector embeddings within specialized databases, optimizing prompt engineering frameworks, and orchestrating complex automation flows using n8n and Flowise. You will closely collaborate with data engineering teams to ingest diverse text corpora, establish rigorous evaluation benchmarks for model hallucination detection, and deploy AI agents that autonomously execute enterprise tasks while adhering to strict security and privacy standards.

Key responsibility

• Design and implement end-to-end Retrieval-Augmented Generation (RAG) architectures utilizing Python, LangChain, and vector databases to enhance context-aware model responses.
• Integrate third-party LLM providers including OpenAI API and Claude API into existing enterprise data processing pipelines via secure RESTful webhooks and custom APIs.
• Develop, test, and refine advanced prompt engineering methodologies to maximize task accuracy and minimize token consumption across diverse operational use cases.
• Build visual workflow automations and multi-agent AI deployments using orchestration tools such as n8n, Flowise, and Zapier Automation.
• Fine-tune open-source Large Language Models on domain-specific datasets using PyTorch, Hugging Face transformers, and efficient parameter-tuning techniques.
• Monitor, debug, and optimize model performance metrics, latency, and throughput in production environments deployed on cloud infrastructure.
• Collaborate with data governance teams to ensure all generative AI implementations comply with enterprise data privacy, security, and ethical AI guidelines.

Required Qualification and Skills

• Bachelor's degree in Computer Science, Data Science, Artificial Intelligence, or a related quantitative discipline with 0-1 years of hands-on technical experience.
• Strong programming proficiency in Python along with experience utilizing modern machine learning libraries and APIs.
• Deep working knowledge of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and prompt engineering techniques.
• Familiarity with vector databases (e.g., Pinecone, Milvus, Chroma) and embedding generation pipelines.
• Experience integrating APIs and webhooks, and building automation workflows using tools like n8n, Flowise, or Zapier.
• Foundational understanding of machine learning frameworks such as PyTorch, TensorFlow, or scikit-learn.
• Excellent analytical, problem-solving, and cross-functional communication skills with a strong passion for generative artificial intelligence.

Looking to get Placed? Try our Placement Guarantee Plan

Get Hired

Benefits Included

• Competitive starting salary package benchmarked against top-tier technology industry standards in India.
• Comprehensive health insurance coverage extending to immediate family members and dependents.
• Flexible work arrangements with standard work-from-office infrastructure and high-speed connectivity support.
• Dedicated annual learning and development budget for obtaining cloud and artificial intelligence certifications.
• Regular wellness programs, team-building activities, and structured mentorship from seasoned AI researchers.
• Generous paid time off, parental leave policies, and performance-based annual retention bonuses.

A Day in the Life

Your day begins with reviewing model evaluation metrics and analyzing failure cases from recent RAG deployment runs. You will spend the morning writing custom Python scripts to optimize vector retrieval speeds and experimenting with new prompt structures for an upcoming client-facing chatbot. Post lunch, you will collaborate with the data engineering squad to configure an n8n webhook workflow that automates document ingestion. The afternoon involves debugging an API integration issue with the Claude API, documenting pipeline updates, and participating in a sprint planning session to map out upcoming AI agent deployment milestones.