Experienced LLM Engineer

Saroe, Inc. is hiring an Experienced LLM Engineer on behalf of our client, a forward-thinking technology company specializing in Generative AI solutions. This role is ideal for candidates with hands-on experience in GenAI development and a strong foundation in backend engineering. As part of this position, you will work on diverse and impactful projects, including client-facing and internal initiatives to develop innovative AI-driven use cases such as AI assistants and content generation tools.

Key Responsibilities
• RAG Pipeline Development: Design and implement Retrieval-Augmented Generation (RAG) pipelines for efficient, context-aware information retrieval.
• Prompt Engineering: Apply prompt tuning and fine-tuning strategies to enhance the relevance and quality of AI outputs.
• API Development: Build, maintain, and optimize backend APIs using FastAPI or similar frameworks for seamless integration with AI applications.
• Model Deployment: Deploy and manage Large Language Models (LLMs) such as OpenAI models or equivalents, ensuring production readiness and performance.
• Cloud Integration: Utilize cloud platforms like AWS or Azure to deploy, scale, and optimize AI models.
• Validation and Testing: Validate and test generative AI outputs to ensure reliability and high-quality performance.
• Vector Databases and Caching: Work with vector databases and caching systems to enhance data retrieval and minimize latency.
• Collaboration: Collaborate with data scientists, engineers, and stakeholders to deliver robust AI solutions for diverse projects.
• Performance Optimization: Profile, debug, and optimize machine learning systems to ensure scalability and optimal system performance.

Qualifications and Requirements
• Experience:
• At least 9+ months of relevant experience in Generative AI development.
• 2+ years of overall experience in software development or machine learning engineering.
• Technical Skills:
• Proficiency in Python programming.
• Experience with FastAPI or similar frameworks for backend API development.
• Hands-on expertise with large language models (e.g., OpenAI or similar).
• Proficiency with cloud platforms like AWS or Azure for deployment and scaling.
• Experience deploying LLM-based products into production environments.
• Project Experience:
• Involvement in AI-driven projects such as building AI assistants or content generation tools.
• Familiarity with RAG pipeline creation, prompt tuning, and validation of generative outputs.
• Experience with vector databases and caching for optimizing data retrieval.
• Soft Skills:
• Strong communication skills for collaborative teamwork and occasional client interactions.
• Problem-solving mindset and ability to work in dynamic environments.

Performance Expectations
• Design and implement efficient RAG pipelines and GenAI solutions aligned with project goals.
• Optimize backend systems and APIs for seamless integration with AI models.
• Ensure scalable, reliable, and high-performance deployments.
• Collaborate effectively with cross-functional teams and stakeholders.
• Contribute to client-facing projects, including interviews and presentations, when required.

Location

This position is remote,

Why Join Us?

At Saroe, Inc., we collaborate with industry leaders to provide transformative technology solutions. This role offers an opportunity to work on high-impact Generative AI projects, contributing to advancements in AI innovation.

How to Apply

If you are passionate about pushing the boundaries of Generative AI and ready to make an impact, we want to hear from you. Apply now to be a part of this exciting journey!