Designing, implementing, and optimizing GenAI applications for live, real-time deployments, including prompt engineering, vector databases, and agentic tools.
Requirements
- AI/ML Foundations: Familiarity with NLP, machine learning fundamentals, and deep learning frameworks (e.g., PyTorch or TensorFlow).
- Programming Skills: Solid Python background; comfort with libraries like NumPy, pandas, and familiarity with concurrency or parallelism is a plus.
- Hands-On Project Experience: Coursework or personal projects involving LLMs, vector databases, or text analysis; experience deploying real-time AI solutions is a bonus.
- Cloud Familiarity: Exposure to either Azure or AWS; ability to learn how to set up virtual machines, container services, or serverless functions.
- Agentic Frameworks: Experience or interest in frameworks like AutoGen, Crew, or other agentic systems for automating AI-driven tasks.
- MLOps & Tooling: Familiarity with containerization (Docker), CI/CD pipelines, or other DevOps practices for robust AI model deployment.
- Cloud Deployment: Use either Azure or AWS to configure and deploy AI models, ensuring scalability, security, and optimal performance for live applications.
Responsibilities
- Advanced Python Proficiency: Write clean, efficient, and maintainable Python code for data preprocessing, model training, and integration with production systems.
- Prompt Engineering: Design, test, and refine prompts to produce optimal AI-driven outputs (chatbots, content generation, etc.).
- Retrieval-Augmented Generation (RAG): Implement techniques that combine model outputs with external data sources to improve accuracy in real-world scenarios.
- LangChain & Langraph Integration: Leverage these libraries to build modular, scalable AI pipelines for language-based tasks.
- Vector Database Management: Work with databases like Pinecone, Faiss, or other vector stores to store embeddings and enable efficient semantic search.
- Chunking Techniques: Develop methods to split large documents into manageable sections, ensuring more accurate and efficient retrieval and generation.
- Streamlit (or Similar) Prototyping: Create user-facing dashboards or internal tools to visualize and interact with AI functionalities.
Other
- Education: Bachelor's degree in Computer Science, Data Science, Engineering, or related field (or equivalent practical experience).
- Adaptability: Excitement about experimenting with new libraries (LangChain, Langraph) and emerging large language models.
- Curiosity & Team Spirit: Eagerness to learn, collaborate, iterate quickly, and stay current on GenAI trends.
- Collaboration & Documentation: Participate in code reviews, maintain thorough documentation, and share best practices with cross-functional teams.
- Full-Stack Knowledge: Understanding of front-end technologies for better integration of AI-backed features in web or mobile interfaces.
