Highlights
Designing agent-based architectures, fine-tuning LLMs, developing NLP solutions, optimizing models, and collaborating on cross-functional teams.
Description
We are seeking a proficient AI Engineer with a robust background in Agentic Artificial Intelligence and Natural Language Processing (NLP). This role requires the candidate to design, develop, and deploy intelligent systems using advanced Large Language Models (LLMs), multi-agent frameworks, and autonomous agents. The ideal candidate will have hands-on experience with cutting-edge tools such as CrewAI, LangGraph, AutoGen, LangChain, and similar platforms.
- Design agent-based architectures for real-world problem-solving
- Build multi-agent workflows for task orchestration, decision-making, and execution
- Integrate LLMs with various tools, APIs, and memory systems to enhance model performance
- Fine-tune pre-trained models like Mistral Large, Gemini Flash, and OpenAI models for specific applications
- Create NLP solutions for summarization, classification, and text generation
- Contribute to internal or open-source model repositories by developing new modules and features
- Pre-process and analyze large-scale datasets using advanced data engineering techniques
- Collaborate with cross-functional teams on scalable data pipelines and evaluation metrics
- Optimize models for performance, latency, and scalability in production environments
- Stay current with the latest advancements in LLMs, agentic architectures, and AI safety practices
- Maintain comprehensive technical documentation for models and agent workflows
- Present findings to both technical and non-technical stakeholders at various levels of the organization
The role demands a combination of strong problem-solving skills, deep technical expertise in programming languages like Python, and experience with frameworks such as PyTorch or TensorFlow. A solid understanding of distributed systems, large-scale data processing, and AI safety is crucial for success.
Skills