Generative AI Engineer - LLM Models (5-10 yrs)

Roles and responsibilities :

1.Prompt Engineering : Develop and fine-tune complex prompts for natural language processing (NLP) and other generative AI models to ensure high-quality outputs, ensuring that prompts are effective, efficient, and scalable.

2.Python Programming : Write clean, maintainable, and efficient Python code for AI model implementation, data manipulation, and integration with existing software systems.

3.Collaboration and Mentorship : Work closely with data scientists, product managers, and software engineers to integrate generative AI models into production systems. Provide technical mentorship to junior engineers.

4.Design, develop, and optimize generative AI models (such as GPT, DALL-E, and similar models) for a variety of applications, from content generation to automation.

Skills Required :

1. 2 years for experience on small LLM models for specialized use cases.

2. Worked on the RAG Pipeline.

3. Developed a Framework to streamline the development, testing, and deployment of Gen AI Applications with prompt engineering.

4. Experience on LLM models utilizing the Lang chain Framework.

5. Implementation experience on storage and indexing of embedding data in the Vector database

6. Created a conversational AI bot based on Gemini models, simplifying user interactions through natural language.

7.Deployed a Deep Learning solution with Rest API built on Fast API Framework.

8. Experience or knowledge of test-Driven development and behaviour driven development

9. Able to interpret a business requirement and transform it into an executable code

10.At ease to handle a broad set of data coming into a variety of formats

11. Fluent in English

12.Familiarity with SDLC and development best practices

13. A team player with excellent communication skills, enjoying working collaboratively

Mandatory Skills :

- GEN AI with Prompt Engineering, Python Programming