Location: Remote | Type: Full-Time | Team: AI Product Engineering

*Due to operational requirements, candidates located in the Americas will be considered for this role.

About the Role

Our hiring partner is reimagining software development through an AI-first lens — where intelligent agents, automated reasoning, and LLM-powered tools accelerate every stage of the SDLC. As a Senior AI Engineer, you’ll architect, test, and deploy next-generation AI systems that make both developers and products smarter.

You’ll work across C#/.NET services, AWS infrastructure, and React-based apps to design AI-native systems enhanced by human-in-the-loop feedback, continuous evaluation, automated testing, and agentic coding workflows using tools like GitHub Copilot and Claude Code.

This is a hands-on role at the intersection of AI orchestration, agentic coding, and full-stack engineering — ideal for someone who pairs deep technical judgment with a strong curiosity for how intelligent systems evolve in production.

What You’ll Do

• Design, build, and maintain LLM-based services, AI agents, and orchestration workflows using Semantic Kernel and Microsoft Agent Framework.
• Apply advanced prompt engineering, agentic patterns, and model evaluation techniques to improve reliability, precision, and adaptability.
• Architect LLM orchestration and vector memory systems connecting backend APIs with dynamic front-end experiences.
• Implement retrieval-augmented generation (RAG) pipelines with vector databases (Weaviate, Pinecone, Milvus) for structured and contextual reasoning.
• Develop and maintain performant C#/.NET and TypeScript/Node services that integrate AI directly into application logic.
• Design and execute automated testing strategies for AI features, covering unit, integration, and simulation-based tests for agent behavior and LLM responses.
• Manage source control, branch strategy, and CI/CD pipelines using GitHub, ensuring scalable, high-quality collaboration.
• Use agentic development tools (GitHub Copilot, Claude Code, Cursor, etc.) to prototype, refactor, and accelerate daily coding workflows.
• Work with subject matter experts to define evaluation pipelines that use real and synthetic data to reinforce quality and compliance.
• Collaborate across disciplines to define AI design standards, testing practices, and observability frameworks for production reliability.
• Mentor peers in AI-first, test-driven, and agent-assisted engineering, fostering reproducibility and experimental rigor.

What We’re Looking For

• 5+ years of software engineering experience in modern cloud/SaaS environments.
• Proficiency with C#/.NET, TypeScript/React, AWS, and GitHub-based version control workflows (branches, pull requests, code reviews).
• Proven experience in LLM orchestration, agent frameworks, and prompt engineering for production systems.
• Strong hands-on experience with agentic coding tools such as GitHub Copilot, Claude Code, or comparable AI coding assistants — and a proven ability to integrate them effectively in daily development.
• Solid background in software testing, including unit testing, integration testing, and automated evaluation of AI workflows.
• Hands-on experience with vector databases, RAG pipelines, and semantic search systems.
• Familiarity with AI SDKs and orchestration frameworks (Semantic Kernel, LangChain, etc.).
• Strong foundation in API and data security, especially in regulated or compliance-sensitive environments.
• Effective communicator, capable of working asynchronously, documenting clearly, and collaborating through version-controlled workflows.

Nice to Have

• Experience with Python, AI observability, and model-evaluation frameworks (PromptLayer, Traceloop, or similar).
• Background in multi-agent architectures, reasoning pipelines, or adaptive experimentation systems.
• Track record of taking AI-driven products from prototype to production.
• Contributions to AI open-source projects or cross-disciplinary research.