Artificial Intelligence Developer

Role & responsibilities

• Design, build, and deploy solutions that wrap large language models (OpenAI, Anthropic, Claude, Gemini, etc.) for practical business use cases.
• Implement and optimize retrieval-augmented generation (RAG) frameworks using vector databases (e.g., Pinecone, FAISS, Chroma, Milvus).
• Build robust API integrations between AI providers, internal systems, and user interfaces.
• Structure and maintain SQL or NoSQL databases to support knowledge retrieval, model context, and user interaction histories.
• Collaborate with front-end engineers to design user-friendly interfaces for AI chatbots, dashboards, and knowledge assistants.
• Conduct prompt engineering, performance evaluation, and continuous tuning of model responses to improve accuracy and reliability.
• Manage corpus ingestion, vectorization, and updating of proprietary datasets feeding the AI tools.
• Ensure compliance with data governance, security, and privacy best practices related to AI and sensitive data.
• Document architectural decisions, workflows, and model performance. Support agile sprints and cross-team communication.

Preferred candidate profile

• Bachelors or Master’s degree in Computer Science, Artificial Intelligence, Data Engineering, or related field.
• 3–7 years of professional experience in AI development, with at least one end-to-end deployed LLM or AI product.
• Strong programming background in Python (preferred) or C#.
• Experience with LLM APIs (OpenAI, Azure OpenAI, Anthropic, Hugging Face, etc.).
• Solid understanding of RAG architecture and vector database design.
• Experience with RESTful API development and integration.
• Proficiency in SQL (T-SQL, PostgreSQL, MySQL) and general database design.
• Familiarity with LangChain, LlamaIndex, or similar AI orchestration frameworks.
• Working knowledge of cloud platforms (Azure, AWS, or GCP) for hosting AI workloads.
• Understanding of Docker, Kubernetes, or similar container orchestration tools.
• Experience integrating AI with web front ends (React, Next.js, or Streamlit preferred).
• Knowledge of embedding models, prompt engineering, and token optimization.
• Exposure to data transformation pipelines and ETL tools.
• AI/ML certification from a recognized institution (Microsoft, Google, Coursera, etc.).
• Experience working with Git, CI/CD pipelines, and DevOps environments.