Senior AI Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Architect intricate, multi-agent workflows utilizing the Microsoft AI technology stack.

• Design, develop, and implement agents that can manage loops, interruptions, and human-in-the-loop interactions.

• Create dependable "tool layers" that enable LLMs to securely interact with internal APIs, databases, and external SaaS platforms.

• Design persistence layers to effectively manage agent memory, conversational history, and context windows.

• Develop production-quality data retrieval and integration systems. Enhance vector indexing, document chunking, and re-ranking algorithms to ensure precise context retrieval.

• Collaborate with Data Engineers to assemble "Golden Datasets" for agent utilization.

• Construct CI/CD pipelines for AI that incorporate "LLM-as-a-Judge" testing.

• Embed applications with tracing tools to visualize agent reasoning paths, monitor latency, and troubleshoot production failures.

• Monitor token consumption and latency, optimizing prompt density and caching strategies to sustain high performance at manageable costs.

• Quickly validate innovative concepts using cutting-edge models, then refine successful prototypes into maintainable, tested production code.

⛳️ Requirements

• Bachelor’s degree and 5 years of software engineering experience, including exposure to AI/ML applications, OR 9 years of software engineering experience with AI/ML applications.

• Over 2 years of experience specifically in building with LLMs, demonstrating deep familiarity with: Orchestration: LangChain, LangGraph, or similar state-based frameworks.

• Experience with Vector DBs: Pinecone, Weaviate, or pgvector.

• Proficiency in Prompt Engineering: Advanced techniques (Chain-of-Thought, ReAct, Few-Shot).

• Practical experience in not only developing demos but also operating them. You understand how to manage rate limits, context window overflows, and non-deterministic errors.

• Ability to convey the concept of "probabilistic software" to non-technical stakeholders—setting expectations that while agents may not be 100% accurate, they can be 100% useful.

• Strong communication skills, with a background in documenting technical designs, sharing insights, and facilitating team knowledge transfer.

🏝️ Benefits

• Opportunity to design and develop the next generation of enterprise AI agents.

• A collaborative atmosphere that promotes experimentation and innovation.