We are seeking a bright and ambitious Junior AI Developer with a strong foundation in data science and software engineering to join our team. In this role, you will be at the forefront of developing and implementing AI solutions. Your primary mission will be to design, build, and deploy sophisticated tools that leverage Large Language Models (LLMs) to analyze millions of documents at scale, identifying critical information such as Personally Identifiable Information (PII) and sensitive financial data.
You will be responsible for the full lifecycle of AI feature development, from creating backend services from scratch to integrating powerful models with our modern web applications (Next.js, Python, TypeScript). If you are a creative problem solver, passionate about building robust and economically efficient systems, and eager to tackle large‑scale data challenges in a cost‑effective manner, we encourage you to apply.
Key Responsibilities
- Develop, train, and fine‑tune AI/ML models, with a focus on LLMs, for high‑accuracy information extraction and analysis from vast, unstructured document sets.
- Build and deploy robust backend services and APIs from scratch in Python to serve AI models and manage data processing workflows.
- Analyze and optimize the performance and cost of AI models and data pipelines, ensuring solutions are not only powerful but also economical to operate at scale.
- Integrate AI services and models with our front‑end applications (Next.js/TypeScript) and existing backend infrastructure.
- Implement and optimize advanced AI techniques, including embedding generation, Retrieval‑Augmented Generation (RAG), and vector search.
- Manage and interact with vector databases (e.g., Pinecone, Weaviate, Milvus, Chroma) to support scalable similarity searches.
- Leverage containerization technologies like Docker and Kubernetes to package and deploy applications and AI models efficiently.
- Work within our cloud infrastructure (AWS, GCP, Azure) to build and scale data pipelines and AI‑powered services, with a strong focus on resource optimization and cost management.
- Design and manage secure code execution environments for dynamic model interaction and analysis.
Qualifications & Skills
- Strong proficiency in Python and experience building backend applications or services.
- A practical mindset for building cost‑effective solutions, with an understanding of the resource and cost implications of technical choices, especially within a cloud and LLM context.
- A solid understanding of the data science lifecycle and core machine learning principles.
- Demonstrable knowledge of Large Language Models (LLMs) and their underlying concepts, including:
- Embeddings and their use in semantic search
- Retrieval‑Augmented Generation (RAG) patterns
- Vector databases and their role in AI applications
- Prompt engineering and fine‑tuning techniques
- Foundational experience with containerization technologies (e.g., Docker) and an understanding of their importance in modern application deployment.
- Familiarity with cloud computing platforms (e.g., AWS, GCP, Azure) and basic infrastructure concepts.
- Exposure to or an interest in front‑end technologies like React and Next.js.
- A portfolio (e.g., GitHub profile or website) showcasing relevant personal or academic projects is required.