GEN AI Software Engineer

Job Title: GEN AI Software Engineer

Contract Period: 9/15/2024 - 8/31/2025

Work location: Ridgefield Park, NJ

We're seeking a skilled engineer to lead the development of cutting-edge RAG applications using state-of-the-art LLM technologies. The ideal candidate will have a strong background in AI and NLP, with hands-on experience in building and optimizing LLM-based systems. This role requires expertise in integrating LLM solutions via APIs with both third-party tools and in-house applications. Experience with AWS Bedrock is highly valued, and familiarity with microservices architecture in cloud environments is a significant plus.

Primary Responsibilities:

• Design and implement RAG (Retrieval-Augmented Generation) systems
• Integrate and optimize Large Language Models (LLMs) via APIs
• Develop efficient information retrieval and extraction systems
• Build and manage databases and vector stores
• Apply Natural Language Processing (NLP) techniques
• Monitor performance and continuously improve systems
• Integrate LLM solutions with other third-party tools and in-house applications
• Design and implement APIs for seamless integration of LLM capabilities

Requirements:

• Bachelor's degree or higher in Computer Science, Artificial Intelligence, or related field (Master's preferred)
• Proficiency in Python programming
• Deep understanding of LLMs, RAG systems, and API integration
• Experience with NLP and machine learning
• Strong skills in database and API development
• Knowledge of distributed systems and cloud computing
• Expertise in integrating AI models with various software solutions

Preferred Qualifications:

• Contributions to open-source LLM projects
• Experience building AI systems in large-scale production environments
• Experience with vector databases (e.g., Pinecone, Faiss)
• Proficiency with relevant libraries such as Transformers, Hugging Face
• Experience with AWS Bedrock for AI/ML model deployment and management
• Experience with microservices architecture (MSA) in cloud environments
• Familiarity with LLM API providers (e.g., OpenAI, Anthropic, Cohere)

Suggested Tech Stack:

• Language: Python
• Frameworks: PyTorch or TensorFlow, FastAPI or Flask for API development
• Databases: PostgreSQL, MySQL, MongoDB,
• Vector Stores: Pinecone, Faiss
• Cloud Platforms: AWS (including Bedrock), Google Cloud, or Azure
• Integration Tools: Apache Kafka, RabbitMQ