We are seeking an AI Engineer with strong proficiency in Python and hands-on experience in building AI-powered applications. The ideal candidate should have experience working with FastAPI, Langchain, and Pydantic, along with a solid understanding of Generative AI concepts, Large Language Models (LLMs), Prompt Engineering, and Retrieval-Augmented Generation (RAG).
Key Responsibilities:
- Develop, integrate, and optimize AI-powered applications using FastAPI and Langchain.
- Design and deploy APIs using FastAPI with Pydantic for data validation.
- Implement and fine-tune solutions leveraging Large Language Models (LLMs).
- Build and optimize Prompt Engineering pipelines for LLM interactions.
- Design and implement Retrieval-Augmented Generation (RAG) solutions for enhanced contextual responses.
- Collaborate with data scientists, product managers, and engineers to deliver high-quality AI applications.
- Continuously research and experiment with advancements in Generative AI technologies.
Key Skills & Technologies:
-
Programming:
Python (Intermediate to Advanced) -
Frameworks & Libraries:
- FastAPI (API development)
- Langchain (LLM integrations & workflows)
- Pydantic (Data validation and settings management)
-
AI/ML Concepts:
- Generative AI (Basics)
- Large Language Models (LLM) Understanding architecture, capabilities, and limitations
- Prompt Engineering Techniques for effective LLM interactions
- Retrieval-Augmented Generation (RAG) Building hybrid retrieval-generation systems
-
Version Control:
Git, GitHub/GitLab -
CI/CD:
Familiarity with deployment pipelines (optional)
Preferred/Optional (Good to Have):
- Experience with AI Agent Frameworks such as:
- Knowledge of Vector Databases (e.g., FAISS, Chroma)
- Cloud Platforms (AWS, Azure, GCP)
- Containerization (Docker)
Perform an action: We are at these locations
Ignitho teams operate globally from USA, UK, India, Sweden, and Costa Rica.