Design, develop, and optimize agentic AI systems and AI-powered product capabilities
Partner with team members to gather, clarify, and establish requirements for AI products
Support the deployment, monitoring, and maintenance of AI products in production environments
Help define and track key performance metrics such as accuracy, retrieval rates, and hit rates, and assist in identifying corrective actions when performance declines
Evaluate and implement tools to monitor AI product performance and reliability in production
Create and maintain technical documentation related to product design, model selection, experimentation, and production infrastructure
Collaborate with engineering and non-technical stakeholders to communicate AI concepts clearly and support adoption of AI solutions
Stay current on emerging trends, tools, and best practices in artificial intelligence, machine learning, and GenAI applications
Requirements
Currently pursuing or recently completed a Bachelor’s degree in Computer Science, Engineering, or a related technical field
Proficiency in Python
Experience building and deploying at least two LLM-based or NLP-heavy applications in real-world or project-based settings, ideally using frameworks such as LangGraph, LangChain, or AutoGen
Strong mathematical, analytical, and problem-solving skills
Experience with retrieval systems, embeddings, and vector databases such as Weaviate or Pinecone
Ability to structure and execute an agentic AI project from concept through implementation
Familiarity with cloud platforms such as AWS
Experience using version control tools such as Git
Ability to leverage coding agents or AI-assisted development tools to accelerate software development
Strong communication and collaboration skills, with the ability to work effectively in a team environment
Preferred Qualifications: Knowledge of SQL and NoSQL databases, including writing queries, query optimization, and schema design
Experience developing APIs using tools such as FastAPI or Flask
Understanding of machine learning algorithms and language models such as GPT, BERT, or similar technologies
Familiarity with containerization and orchestration tools such as Docker and Kubernetes
Ability to explain technical AI concepts to non-technical stakeholders in a clear and approachable way.