Senior Lead Engineer - LLM

Role: Full Stack Developer Large Language Model (LLM)
Total Experience: 7 to 12 Years

Notice Period: Immediate to 15 days maximum
Location: Hyderabad

Requirements

Job Description:
We are seeking a talented Full Stack Developer to join our team and play a pivotal role in developing cuttingedge web applications for large language models (LLMs). You will be responsible for designing developing and deploying web applications that harness the power of LLMs to solve realworld problems. Additionally you will contribute to the opensource community by collaborating on projects that enrich and enhance LLM capabilities.

Essential Duties and Responsibilities:

Design develop and implement orchestrators for LLMs such as Lang Chain Llama Index Hugging face haystack to enhance their capabilities in areas of natural language generation machine translation text summarization and code generation.

Thoroughly test and debug LLM application to ensure their functionality and compatibility with different LLM models.

Document and maintain the codebase to ensure clarity and ease of future development.

Stay up to date with the latest advancements in LLM technology emerging addon development trends and the evolving capabilities of LLM platforms.

• Collaborate with AI researchers and engineers to understand the requirements and technical specifications of LLMpowered web applications.
  
• Select and utilize appropriate frontend and backend technologies such as React JavaScript Python and Django to build robust and scalable web applications.
  
• Contribute to opensource LLM projects by identifying areas for improvement proposing solutions and developing code contributions.
  
• Document and maintain codebase to ensure clarity and ease of future development.
  
• Stay up to date with the latest advancements in LLM technology and web development trends.
  

Qualifications:

• Bachelor s degree in computer science Software Engineering or a related field.
  
• Minimum of 5 years of experience in Machine Learning & Deep learning applications
  
• Minimum of 2 years of experience in Generative AI applications such as LLM
  
• Strong understanding and hands on experience of frontend and backend technologies including Flask & Django using Python language.
  
• Hands on experience on cloudbased services such as Azure OpenAI
  
• Strong understanding of programming languages and frameworks relevant to LLM addon development such as Python Java or JavaScript.
  
• Familiarity with the concepts and principles of natural language processing.
  
• Experience with testing and debugging software applications.
  
• Experience with designing and developing web applications utilizing APIs and microservices will be added advantage.
  
• Familiarity with opensource LLM projects and a passion for contributing to the AI community.
  
• Excellent problemsolving and debugging skills.
  
• Ability to work independently and as part of a team.
  

Benefits

Veltris

Where Innovation Acceleration and Transformation meet to deliver highROI technology and business solutions. Our design thinking approach to agile software development coupled with premium fullstack capabilities and a cuttingedge innovation mindset accelerates timetomarket. This results in longterm strategic and competitive advantages for our clients and partners.

Veltris Innovate Accelerate Transform to enable technologydriven Enterprise Business and Industry transformations.