Junior Retrieval-Augmented Generation And OpenAI API System Developer

What role will you play in the team

As a Junior Retrieval-Augmented Generation and OpenAI API System Developer, you will be an integral part of our advanced artificial intelligence division. Your core focus will involve architecting, developing, and optimizing state-of-the-art semantic search pipelines and generative text applications using cutting-edge language models. You will work closely with senior machine learning scientists and data engineers to integrate foundational LLM APIs with vector databases, ensuring our enterprise clients receive robust, accurate, and context-aware natural language processing solutions tailored to their specific operational workflows and knowledge retrieval requirements.

What you will do

You will actively design and implement data ingestion pipelines that parse unstructured documents, chunk texts intelligently, and generate dense vector embeddings for storage in high-performance vector stores like Pinecone and Milvus. Your daily tasks will include writing clean, modular Python scripts to query Large Language Models, fine-tuning retrieval parameters, crafting advanced prompt engineering strategies, and orchestrating complex multi-step reasoning agents using frameworks such as LangChain and LlamaIndex. Additionally, you will monitor system latency, evaluate response faithfulness using automated benchmarking tools, and collaborate with backend developers to expose these AI capabilities through secure RESTful APIs and webhooks.

Key responsibility

• Design, develop, and maintain advanced Retrieval-Augmented Generation (RAG) pipelines for enterprise document processing and automated question-answering systems.
• Integrate OpenAI API, Claude API, and other hosted Large Language Models into custom backend applications and workflow automation platforms.
• Implement efficient vector database indexing, similarity search queries, and hybrid keyword-semantic retrieval mechanisms.
• Write comprehensive Python scripts utilizing LangChain, LlamaIndex, and vector storage engines for contextual data extraction.
• Optimize prompt engineering templates, few-shot examples, and chain-of-thought instructions to maximize model accuracy and minimize hallucinations.
• Collaborate with DevOps teams to deploy containerized RAG microservices using Docker and Kubernetes on cloud environments.
• Conduct systematic evaluations of LLM output quality, latency bottlenecks, and token usage optimization strategies.

Required Qualification and Skills

• Bachelor's degree in Computer Science, Artificial Intelligence, Data Science, or a related quantitative discipline with 0-1 years of practical software development experience.
• Strong proficiency in Python programming, asynchronous execution, and object-oriented design principles.
• Hands-on experience working with OpenAI API, Claude API, and hugging face transformers for generative AI tasks.
• Familiarity with vector databases (Pinecone, Chroma, Milvus, Qdrant) and embedding generation techniques.
• Working knowledge of RAG frameworks like LangChain, LlamaIndex, and agentic workflow orchestration tools.
• Understanding of database management systems including PostgreSQL and MongoDB for metadata storage.
• Strong analytical mindset, problem-solving skills, and ability to write clean, well-documented code.

Benefits Included

• Competitive entry-level annual compensation package with performance-based quarterly reviews and bonuses.
• Comprehensive health, medical, and life insurance coverage for employee and immediate family dependents.
• Flexible hybrid work arrangement options promoting healthy work-life balance and remote productivity.
• Generous learning and development stipend for attending AI conferences, certifications, and workshops.
• Access to mental health support platforms, wellness programs, and modern collaborative office spaces.
• Paid time off, parental leave, and regular team-building events in major metropolitan hubs.

A Day in the Life

Your typical day begins by reviewing system monitoring logs for our production RAG pipelines to identify any retrieval errors or latency spikes. You spend the morning optimizing embedding chunk sizes and testing a new prompt template with the OpenAI API to improve contextual accuracy for a client's customer support bot. After a mid-day sync with the data engineering team, you spend the afternoon writing Python code to integrate a new vector database cluster, followed by peer-reviewing pull requests and documenting your API integration endpoints before logging off.