A leading AI solutions company in Kolkata is seeking a professional with 4-10 years of experience to design and develop application solutions using generative models and vector databases. The ideal candidate will optimize and fine-tune models for performance while collaborating with cross-functional teams. Proficiency in Python and hands-on experience with generative text models, as well as knowledge of AWS and serverless architecture, are essential. This role offers the opportunity to work on cutting-edge AI technologies in a dynamic environment.
Qualifications
4-10 years of experience in a related field.
Familiarity with other programming languages is a plus.
Experience with Azure or GCP is desirable.
Responsibilities
Design and develop application solutions using generative models.
Optimize and fine-tune generative models for performance and efficiency.
Communicate complex technical concepts to non-technical stakeholders.
Skills
Python proficiency
Prompt engineering
Generative text models (Claude, OpenAI GPT, Gemini)
AWS Bedrock
AWS serverless architecture
Tools
Git
GitHub Copilot
Job description
Experience
4-10 Years.
Key Responsibilities
Design and develop application solutions using generative models, RAG and vector database and vector search.
Collaborate with cross-functional teams to integrate generative AI solutions into existing workflow systems.
Research and stay current on the latest advancements in generative AI technologies, methodologies, and best practices.
Optimize and fine-tune generative models for performance, scalability, and efficiency.
Troubleshoot and resolve issues related to generative AI models, implementations, and workflows.
Create and maintain comprehensive documentation for generative AI models and their applications.
Build efficient data pipelines and manage large datasets for model training and evaluation.
Measure model outputs using appropriate metrics, with awareness of bias and fairness issues.
Implement and use AI coding assistants (e.g., GitHub Copilot) and version control (Git).
Conduct rigorous testing and build scalable, maintainable systems.
Read, analyze, and implement recent AI research papers; conduct experiments as needed.
Communicate complex technical concepts and findings to non-technical stakeholders.
Required Qualifications
Strong proficiency in Python and effective prompt engineering techniques; familiarity with other programming languages is a plus.
Hands-on experience with leading generative text models (e.g., Claude, OpenAI GPT, Gemini), including model fine-tuning and customization.
Proficiency in AWS Bedrock, including model access and knowledge base implementations; experience with Azure OpenAI.
Solid experience with AWS serverless architecture; familiarity with Azure or GCP is desirable.