AI Engineer

About the Role:
We are hiring an innovative AI Developer to create, test, and integrate LLM-based multi-agent systems into our AI-powered Co-pilot IDE. The role involves crafting intelligent agents that collaborate seamlessly, enhancing productivity in IDE environments. A focus on multi-agent collaboration frameworks and RAG pipelines is essential.

Key Responsibilities:

• Design and integrate multi-agent systems powered by LLMs for IDE environments.
• Develop and test robust model-serving pipelines and proxies using tools like TorchServe, Triton, or FastAPI.
• Fine-tune LLMs using methods such as LoRA, QLoRA, or Prompt Tuning.
• Implement multi-agent frameworks like CrewAI, AutoGen, or custom frameworks for agent collaboration.
• Develop and optimize RAG pipelines and evaluate their performance with tools like LangChain or Haystack.
• Conduct model performance testing with domain-specific metrics to ensure optimal results.
• Integrate AI solutions with mobile application frameworks like React Native, Flutter, or Kotlin.
• Ensure robust data pipelines to support both multi-agent and model integration workflows.

Required Qualifications:

• Academic Background: M.Sc. or Ph.D. in AI, Computer Science, or a related discipline.
• Experience with multi-agent systems, LLM fine-tuning, and model deployment.
• Strong programming skills in Python, with additional basic knowledge of C++ and Rust.
• Familiarity with multi-agent system development frameworks like CrewAI, AutoGen, or similar tools.
• Basic understanding of mobile application development frameworks.
• Proficiency with deep learning libraries like PyTorch and TensorFlow.
• Experience in RAG performance testing, model benchmarking, and optimization.
• Previous work on search systems, recommendation engines, or scalable AI systems is a plus.