Junior RAG Implementation Engineer

What role will you play in the team

As a Junior RAG Implementation Engineer, you will be instrumental in bridging the gap between raw unstructured enterprise data and advanced generative AI models. Your primary focus will be designing and executing robust data ingestion pipelines, vector database storage solutions, and context-retrieval mechanisms that empower custom applications to deliver highly accurate, hallucination-free insights. You will collaborate closely with machine learning researchers and backend developers to build scalable AI systems.

What you will do

You will write clean, maintainable Python code to parse complex documents, generate vector embeddings, and integrate proprietary datasets into high-performance vector databases. Additionally, you will benchmark retrieval accuracy, fine-tune chunking strategies, and construct seamless APIs to serve context-aware responses to downstream applications while ensuring optimal latency and strict adherence to data privacy standards.

Key responsibility

• Develop, test, and maintain robust data ingestion pipelines utilizing Python for parsing and cleaning multi-format enterprise documents.
• Design, implement, and optimize vector database architectures and indexing strategies for rapid similarity searches.
• Integrate state-of-the-art Large Language Models via APIs to construct sophisticated Retrieval-Augmented Generation workflows.
• Evaluate and benchmark retrieval precision, semantic relevance, and overall system response times continuously.
• Collaborate with cross-functional software teams to deploy scalable microservices capable of handling high-throughput AI inference queries.
  
• Monitor production vector store performance and troubleshoot embedding generation bottlenecks or memory leaks.

Required Qualification and Skills

• Bachelor's degree in Computer Science, Data Science, Artificial Intelligence, or a closely related technical field.
• Demonstrated hands-on experience utilizing Python programming languages for advanced data manipulation and backend logic.
• Solid understanding of vector embedding concepts, semantic search algorithms, and Large Language Model architectures.
• Familiarity with cloud-based vector databases, relational database management systems, and SQL querying.
• Knowledge of prompt engineering techniques, contextual token optimization, and API integration protocols.
• Strong analytical problem-solving skills, coupled with a capacity to debug complex machine learning pipelines effectively.

Benefits Included

• Competitive annual compensation package structured with performance-based bonuses and annual appraisals.
• Comprehensive health insurance coverage including medical, dental, and vision plans for employees and dependents.
• Flexible working hours with robust remote work and hybrid infrastructure support.
• Generous paid time off, maternal and paternal leave policies, and mental health wellness days.
• Continuous learning stipend allocated for attending international AI conferences, certifications, and technical workshops.
• Dynamic, collaborative startup culture equipped with modern office spaces, ergonomic workstations, and catered daily snacks.

A Day in the Life

Your typical day begins with reviewing automated pipeline logs and analyzing retrieval latency metrics from yesterday's production runs. You will spend the morning optimizing document chunking algorithms in Python and testing new vector indexing parameters. In the afternoon, you will collaborate in a sync meeting with the backend team to integrate a newly updated OpenAI API endpoint, followed by debugging embedding generation errors and documenting your code modifications before logging off.