Introduction & Summary:
The candidate is responsible for designing, developing, and implementing robust AI applications that leverage large language models (LLMs) within agentic systems to enhance business processes and efficiency.
Main Responsibilities:
- Design and build LLM-powered applications and agentic systems.
- Implement Retrieval-Augmented Generation (RAG) pipelines at scale.
- Orchestrate agents and integrate tools using frameworks like LangGraph and OpenAI Assistants.
- Manage LLMOps and CI/CD for prompts and agents.
- Ensure safety, security, and governance in AI implementations.
- Optimize inference performance and cost management strategies.
- Conduct automated testing and evaluations for AI applications.
- Handle data engineering for Generative AI applications.
- Maintain observability and reliability of systems.
- Transition research outputs to production applications.
- Collaborate with cross-functional teams for project success.
Key Requirements:
- Strong programming skills (Python required; TypeScript/Node a plus).
- Solid understanding of machine learning and statistics.
- Experience with ML pipeline development and deployment.
- Knowledge of cloud services (Azure/AWS/GCP).
Nice to Have:
- Familiarity with LLMs and transformers.
- Hands-on experience with agentic frameworks.
- Expertise in retrieval techniques and domain adaptation.
- Proficiency in data engineering and big data technologies.
- Knowledge of vector databases and search systems.
- Experience with MLOps practices.
- Understanding of multimodal AI integration.
- Exposure to frontend technologies for AI applications.
Other Details:
This role offers an opportunity to work in a dynamic environment with a focus on innovative AI solutions. Ideal candidates are those who thrive in fast-paced settings and have a passion for advancing technology.