What You'll Do
Design and lead the implementation of intelligent, stateful AI agents using Python and modern agentic frameworks, establishing technical standards and guiding engineering teams. Drive integration of AI solutions with enterprise systems, databases, and external APIs to enable seamless workflows across the product stack.
Assess and select foundation models based on performance, cost, and suitability for specific use cases. Own the full lifecycle of AI agent development—from concept through deployment—working closely with product, research, and engineering teams to deliver robust, scalable solutions.
Diagnose and resolve complex issues in production AI systems, ensuring high reliability and performance. Develop evaluation frameworks to measure agent accuracy, latency, and tool usage, and lead improvements across the organization. Promote best practices in documentation and architectural decision-making to ensure long-term maintainability.
Requirements
- Proven ability to design and implement multi-step, tool-using agents using frameworks like LangChain or Autogen.
- Strong grasp of prompt engineering, context handling, and LLM behaviors including hallucinations and temperature effects.
- Experience implementing reasoning techniques such as Chain-of-Thought, ReAct, and Tree-of-Thought.
- Skilled in securely connecting agents to external systems, APIs, and databases in complex environments.
- Proficient in building and optimizing RAG pipelines using vector databases and hybrid search methods.
- Experience defining evaluation metrics and monitoring strategies for production LLM applications.
- Knowledge of security practices including prompt injection defenses and guardrail implementation.
- Expertise in optimizing token usage and latency via model routing, caching, and other advanced techniques.
- Strong programming skills in Python and FastAPI, with experience deploying AI systems on AWS, GCP, or Azure.
Preferred Qualifications
- Advanced degree in Computer Science, AI, Machine Learning, or related field.
- Understanding of core ML concepts such as attention, embeddings, and transfer learning.
- Experience translating academic research into production code.
- Familiarity with parameter-efficient fine-tuning methods like PEFT or LoRA.
Benefits
- Commitment to diversity, equity, and inclusion in hiring and workplace culture.
- Support for global recruitment and team coordination.
- Opportunities to contribute to community initiatives through foundation programs.
