Job Summary
As an ML Application Engineer, you will leverage your expertise in AI and Natural Language Processing to architect and implement cutting-edge solutions involving Large Language Models (LLMs). You will be responsible for designing robust system architectures, integrating and implementing Machine Learning Models for complex applications, and developing conversational frameworks. Your role will encompass enhancing core AI systems with a focus on performance, stability, and modularity, as well as integrating voice processing capabilities.
Key Responsibilities
- System Architecture Design: Design architecture involving AI & LLM integration for core systems to deliver scalable and efficient solutions.
- ML Application Architecture Implementation: Implement various ML Application architectures to tackle different challenging business use cases.
- Conversational Framework Development: Develop comprehensive conversational frameworks, including stage management, conversational flows, and repair strategies.
- Agentic Pipeline and Workflow Design: Design and implement agentic pipelines and multi-agent workflows for seamless integration within complex applications.
- Core AI System Enhancement: Enhance the core AI system focusing on code modularity, testing, performance, latency, and stability improvements.
- Voice Processing Pipeline Enhancement: Refine and enhance existing voice processing pipelines to improve accuracy and efficiency.
- Performance Monitoring: Establish and maintain monitoring systems to track the performance and effectiveness of AI applications, implementing improvements as needed.
- Innovation and Experimentation: Foster a culture of innovation by experimenting with new frameworks, methodologies, and technologies to improve existing systems and develop pioneering AI solutions.
- Quality Assurance: Develop and implement rigorous testing protocols and validation processes to ensure the reliability and robustness of AI systems.
General Qualifications
- Bachelor’s Degree or higher in Artificial Intelligence, Data Science, Computer Science, or a related field.
- Solid foundation in LLM frameworks like Langchain and Llamaindex.
Experience and Skills
- Technical Skills:
- Hands-on experience in developing Retrieval-Augmented Generation (RAG) applications.
- Proficiency in Python programming, including backend frameworks, and experience in system architecture design.
- Experience with LLM frameworks such as Langchain, Llamaindex, and Langgraph.
- Strong understanding of state-of-the-art ML Application architecture and design.
- Expertise in Agentic systems and multi-agent system design.
- Experience in microservices architecture and management.
- Strong research and problem-solving capabilities.
- Soft Skills:
- Excellent communication skills to convey complex technical concepts.
- Critical thinking and problem-solving abilities.
- Adaptable, eager to learn, and committed to continuous personal and professional development.
- Preferred Experience:
- Experienced in Python.
- Basic understanding of deep learning and machine learning.
- Experience in designing production-ready LLM applications.
- Research experience in integrating and implementing ML Application systems.
Work Environment
Office-based environment with potential for hybrid or remote work depending on company policy.
Reporting
This position will report to the Chief Technology Officer.
APPLY