Junior Retrieval-Augmented Generation (RAG) And LLM Fine-Tuning Specialist

What role will you play in the team

You will play a vital role in building cutting-edge generative AI solutions, leveraging advanced Large Language Models and custom Retrieval-Augmented Generation architectures to extract high-value insights from unstructured data corpuses, directly empowering enterprise decision-makers with real-time, context-aware intelligence.

What you will do

You will design, develop, and deploy production-ready LLM applications, integrating Python frameworks with vector databases, fine-tuning pre-trained models using specialized datasets, and establishing robust evaluation pipelines to ensure factual accuracy and minimize hallucination rates across complex domain-specific queries.

Key responsibility

• Develop and maintain scalable RAG pipelines using Python, LangChain, and vector databases like ChromaDB and Pinecone for semantic search applications.
• Fine-tune open-source Large Language Models (LLMs) such as LLaMA and Mistral using domain-specific enterprise datasets for optimal performance.
• Integrate OpenAI API, Claude API, and Hugging Face transformers into custom web applications using APIs and webhooks.
• Build automated automation workflows utilizing make.com, n8n, and Flowise to streamline data ingestion and model inference tasks.
• Collaborate with data engineers to optimize data preprocessing, tokenization, and embedding generation strategies for large-scale document repositories.
• Monitor model drift, latency, and token consumption metrics in production environments to continuously improve system reliability and cost-efficiency.

Required Qualification and Skills

• Bachelor's degree in Computer Science, Data Science, Artificial Intelligence, or a related quantitative field with 0-1 years of hands-on experience.
• Strong programming proficiency in Python, including experience with libraries like PyTorch, scikit-learn, and Hugging Face Transformers.
• Demonstrated practical knowledge of Large Language Models (LLMs), prompt engineering, and Retrieval-Augmented Generation (RAG) frameworks.
• Familiarity with vector databases, relational databases, and SQL for efficient data querying and retrieval operations.
• Experience working with APIs and webhooks, as well as automation platforms such as make.com, Zapier Automation, and n8n.

• Looking to get Placed? Try our Placement Guarantee Plan

  Get Hired
  Excellent analytical, problem-solving, and collaborative communication skills within fast-paced agile development teams.

Benefits Included

• Competitive annual compensation package with performance-linked bonuses and comprehensive health insurance coverage for self and family.
• Flexible working hours with robust remote infrastructure support and dedicated professional development allowances for certifications.
• Opportunities to work directly with global tech leaders on breakthrough generative artificial intelligence and machine learning initiatives.
• Generous paid time off, mental health wellness days, and regular team-building offsites to foster a collaborative culture.

A Day in the Life

Your day begins with a stand-up meeting to review vector search metrics from the previous night's deployment. You then spend the morning writing Python scripts to optimize embedding generation for a new client dataset. Post-lunch, you experiment with prompt engineering techniques to improve LLM response accuracy before integrating a new webhook via n8n.