AI / ML Engineer

We are a forward-thinking technology company dedicated to harnessing the power of AI across various sectors, including HR, facility monitoring, retail analytics, marketing, and learning support systems. Our mission is to transform data into actionable insights and innovative solutions that empower businesses and professionals to thrive.

Key Responsibilities:

• Multi-Agent Architectures: Design and implement multi-agent architectures for customer communication, marketing, management, and data analytics. This includes developing agent communication protocols, distributed AI workflows, task orchestration, agent-based decision making, and autonomous agent coordination.
• Development & Optimization: Design complex LLM interaction architectures to ensure security and high efficiency, tune and optimize LLMs for effective performance, and work with RAG-based architectures, multi-agent LLM systems, LangChain, LangGraph, Claude, GPT, Llama, Mistral, and other models.
• Software Engineering: Utilize the DS and ML Python Stack, including NumPy, Pandas, Hugging Face, and OpenAI API. Work with relational and NoSQL databases, vector databases; utilize Git, CI/CD, Jenkins, and Docker for development processes.

Join Our Team:

We are seeking a skilled AI Engineer to join our dynamic team. In this role, you will play a crucial part in developing multi-agent AI solutions and refining prompts to enhance the quality, relevance, and coherence of LLM-generated content across our diverse applications. You will work alongside data scientists, engineers, and researchers to design and deploy cutting-edge LLM solutions that drive impactful results.

• Collaborate with cross-functional teams to create and deploy innovative LLM-based solutions tailored to specific industry needs.
• Engage in discussions to share insights and strategies for prompt optimization and quality enhancement.

Requirements:

• Proven experience in crafting effective prompts for LLMs to improve content generation.
• Strong analytical skills with the ability to critically assess LLM outputs.
• Experience in building a prompt test environment implemented with Jupyter Notebook.
• Integration of Retrieval-Augmented Generation (RAG) architecture using context from a vector database.
• Knowledge of integrating vector databases (e.g., FAISS, Pinecone, or similar) for context retrieval.
• Experience in leveraging RAG architecture to enhance LLM output using context retrieved from a vector database.
• Familiarity with libraries and tools commonly used for data handling and interactions with vector databases (e.g., Pandas, NumPy).

If you're passionate about developing effective multi-agent architectures and prompts and contributing to our company's mission of innovation, we encourage you to apply!