Staff AI Agent Engineer (Machine Learning)
Shape the future of intelligent systems by leading the design and implementation of AI agents powered by Large Language Models. This role focuses on building adaptive, goal-driven agents capable of reasoning, planning, and integrating seamlessly with enterprise platforms.
Key Responsibilities
- Lead the architecture and development of stateful, scalable AI agents using Python and modern frameworks, establishing technical standards across teams.
- Design integrations between AI agents and enterprise systems, databases, and third-party APIs to enable end-to-end automation and mitigate architectural risks.
- Evaluate foundation models from providers such as OpenAI and Anthropic, selecting optimal solutions based on performance, cost, and use-case alignment.
- Own the full lifecycle of AI agent deployment—from concept through production—for complex, large-scale initiatives, working closely with product and research teams.
- Diagnose and resolve issues in AI systems, ensuring high reliability, performance, and scalability, while guiding peers in advanced debugging techniques.
- Develop evaluation frameworks and monitoring strategies to measure accuracy, latency, and tool usage, driving continuous improvement across AI deployments.
- Document architectural decisions, code practices, and research insights to promote knowledge sharing and long-term maintainability.
- Mentor junior and mid-level engineers, supporting technical growth and fostering a culture of innovation and excellence.
Required Expertise
- Proven experience designing multi-step, tool-using agents using frameworks such as LangChain or Autogen.
- Strong grasp of prompt engineering, context handling, and LLM behaviors including hallucinations and temperature effects.
- Experience implementing reasoning techniques like Chain-of-Thought and multi-agent coordination.
- Skill in building secure, scalable integrations between agents and external systems and APIs.
- Proficiency in designing and optimizing Retrieval-Augmented Generation pipelines using vector databases and hybrid search methods.
- Experience defining evaluation metrics and observability practices for LLM-powered systems.
- Knowledge of security measures against prompt injection and implementation of fallback and guardrail mechanisms.
- Expertise in optimizing token usage and latency through model routing, caching, and performance tuning.
- Experience building agents with long-term memory and advanced planning capabilities using methods like ReAct or Tree-of-Thought.
- Strong programming skills in Python and FastAPI, with experience deploying AI applications on AWS, GCP, or Azure using CI/CD pipelines.
Preferred Qualifications
- Advanced degree in Computer Science, AI, Machine Learning, or a related field.
- Understanding of core machine learning concepts such as attention, embeddings, and transfer learning.
- Experience translating academic research into production-grade AI systems.
- Familiarity with fine-tuning approaches including PEFT and LoRA.
Technology Stack
Python, LangChain, LlamaIndex, Autogen, FastAPI, LLM SDKs, OpenAI, Anthropic, Google AI, Redis, AWS, GCP, Azure, CI/CD, vector databases, RAG, prompt engineering, Chain-of-Thought, Tree-of-Thought, ReAct, Rebuff, Guardrails AI
