Wizdomapp - Artificial Intelligence Developer - LLM (3-4 yrs)

About Wizdom :

Join Wizdom and be part of a revolution in learning! We're a bite-sized, audio-first microlearning app powered by Generative AI. Our mission is to make personal and professional growth accessible to everyone by delivering powerful insights from the world's best books, podcasts, and courses in just 15 minutes. Think "Duolingo" for self-improvement!

With over 200,000 users across 100+ countries and ranked among the Top 10 Educational Apps in India, we're building something extraordinary-and we want YOU to be part of it! At Wizdom, you'll be joining a passionate team dedicated to democratizing knowledge and empowering individuals to reach their full potential.

Role Overview :

We're seeking a talented and passionate AI Developer to join our growing team. You will be responsible for designing, developing, and deploying cutting-edge Generative AI models that power our microlearning platform. You'll have the opportunity to work with large language models (LLMs), leverage tools like LangChain and LlamaIndex, and build scalable backend systems using FastAPI.

Key Responsibilities :

1. AI Model Development :

- Design and implement advanced Generative AI models (e.g., GPT-based, LLaMA, etc.) to support applications across various domains, including text generation, summarization, and conversational agents.

- Utilize tools like LangChain and LlamaIndex to build robust AI-powered systems, ensuring seamless integration with data sources, APIs, and databases.

2. Backend Development with FastAPI :

- Develop and maintain fast, efficient, and scalable FastAPI services to expose AI models and algorithms via RESTful APIs.

- Ensure optimal performance and low-latency for API endpoints, focusing on real-time data processing.

3. Pipeline and Integration :

- Build and optimize data processing pipelines for AI models, including ingestion, transformation, and indexing of large datasets using tools like LangChain and LlamaIndex.

- Integrate AI models with external services, databases, and other backend systems to create end-to-end solutions.

4. Collaboration with Cross-Functional Teams :

- Collaborate with product teams to define project requirements, technical feasibility, and timelines.

- Work with front-end developers to integrate AI-powered functionalities into web applications.

- Model Optimization and Fine-Tuning

- Fine-tune and optimize pre-trained Generative AI models to improve accuracy, performance, and scalability for specific business use cases.

- Ensure efficient deployment of models in production environments, addressing issues related to memory, latency, and resource management.

5. Documentation and Code Quality :

- Maintain high standards of code quality, write clear, maintainable code, and conduct thorough unit and integration tests.

- Document AI model architectures, APIs, and workflows for future reference and onboarding of team members.

6. Research and Innovation :

- Stay updated with the latest advancements in Generative AI, LangChain, and LlamaIndex, and actively contribute to the adoption of new techniques and technologies.

- Propose and explore innovative ways to leverage cutting-edge AI technologies to solve complex problems.

Required Skills and Experience :

- 3 to 4 years of experience in AI/ML development

- Strong experience working with Generative AI models (e.g., GPT-3/4, LLaMA)

- Hands-on experience with LangChain and LlamaIndex

- Proficiency in Python and relevant frameworks (TensorFlow, PyTorch, Hugging Face)

- Strong experience developing RESTful APIs using FastAPI

- Solid foundation in NLP and machine learning techniques

- Familiarity with relational and NoSQL databases

- Experience with Git and CI/CD pipelines

Preferred Skills :

- Familiarity with Docker, Kubernetes, and cloud platforms (AWS, GCP, Azure)

- Experience with data pipelines and frameworks (Apache Spark, Airflow)

- Knowledge of front-end frameworks (React, Vue.js)