Position Overview
We’re looking for a skilled AI Engineer with 3 to 6 years of experience in building intelligent applications powered by Large Language Models (LLMs). This role centers around developing AI Agents for our platform, with a focus on integrating third-party LLM APIs (such as OpenAI, Anthropic, and Google) using advanced prompt engineering and RAG (Retrieval-Augmented Generation) techniques. You’ll be working primarily with Python and FastAPI, designing logic that empowers these agents to handle complex workflows in the e-commerce and retail data space.
What You’ll Do
- Develop AI Agents: Architect, build, test, and maintain the core logic behind our AI agents within FastAPI-based services. Manage agent state, orchestrate tasks, integrate with platform data, and leverage LLM capabilities.
- LLM Integration & Prompt Design: Work with APIs from major LLM providers, crafting and iterating on prompts tailored to retail use cases like summarization, Q&A, and content generation.
- Implement RAG Solutions: Use vector databases (e.g., Pinecone, FAISS) to enrich LLM interactions with relevant context through Retrieval-Augmented Generation techniques.
- Build FastAPI Services: Develop scalable FastAPI microservices to serve and manage agent logic, LLM interactions, and platform-level workflows within containerized environments (Docker, Kubernetes).
- Data Preparation: Process and curate data to support prompt context, RAG pipelines, and potentially model fine-tuning in the future.
- Collaborate Across Teams: Partner with product and engineering teams to deliver AI features and continuously adapt to advancements in the LLM ecosystem. Be ready to contribute to in-house model training and optimization efforts as we grow.
What You Bring
- 3–6 years of hands-on software engineering experience, with a solid focus on AI or ML-based systems.
- Experience integrating external LLMs (OpenAI, Anthropic, Google, etc.) into real-world applications.
- Strong skills in prompt engineering and designing effective interactions with LLMs.
- Proficiency in Python and familiarity with FastAPI for building robust RESTful APIs.
- Practical knowledge in architecting AI-powered features, workflows, or autonomous agents.
- Hands-on experience with RAG implementations and vector databases like Pinecone or FAISS.
- Foundational understanding of ML principles and exposure to tools like PyTorch, TensorFlow, or Hugging Face.
- Comfortable working with cloud platforms (AWS, GCP, or Azure) and containerization tools (Docker, Kubernetes).
- Strong analytical mindset and communication skills.
- Familiar with Agile development methodologies and remote collaboration.
- Eager to grow in the AI space and contribute to future innovations in LLM training and deployment.
- Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or a related discipline.