AI Engineer - Remote Eligible

AI Engineer

You'll work on our product, Progress Agentic RAG, a cutting-edge system that combines retrieval-augmented generation (RAG) and advanced agentic pipelines to transform how humans interact with unstructured data. We're seeking an AI Engineer to help design and build scalable, production-ready components that power our agentic platform.

In this role, you will:

• Architect and implement advanced RAG pipelines, including cutting edge extraction, memory systems, and tool-augmented agents.
• Lead the integration of LLMs with external APIs, databases, and internal knowledge graphs.
• Architect and optimize multi-agent systems, ensuring agents can collaborate, delegate tasks, and interact seamlessly with both internal and external tools and APIs.
• Take part in LLM fine tuning projects, helping plan and architect efficient, reproducible pipelines.
• Mentor junior engineers and collaborate with researchers to bring cutting-edge NLP ideas into production.
• Optimize performance, latency, and cost across the stack.
• Own the lifecycle of NLP components: from design to deployment and monitoring.
• Contribute to internal tooling.

Your background:

• Excellent communication and team collaboration skills.
• 7+ years of experience in software engineering, with at least 5 in NLP or ML.
• Deep understanding of LLMs, Transformers, and RAG architectures.
• Strong Python skills and experience with frameworks like FastAPI and HuggingFace.
• Have experience deploying ML models in production through specialized inference servers such as Triton Inference Server, vLLM, SGLang or TGI.
• Proficient in managing the full ML production lifecycle, including CI/CD pipelines, containerization with Docker, orchestration using Kubernetes, and monitoring of services.
• Worked previously in services deployed in any major cloud provider (AWS, Azure, GCP).
• Familiarity with vector databases.
• Excellent communication and leadership skills.
• Comfortable working in a remote-first environment.

Additionally, it would be beneficial if you have:

• Strong communication and interpersonal skills (spoken and written).
• Experience in building evaluation frameworks for LLM or RAG environments.
• Experience with agentic frameworks or autonomous agents.
• Contributions to open-source NLP or ML projects.
• Passion about staying up to date with the latest NLP research.

If this sounds like you and fits your experience and career goals, we'd be happy to chat.

Compensation:

• Generous remuneration package
• Employee Stock Purchase Plan Enrollment

Vacation, Family, and Health:

• 23 vacation days annually
• Birthday day off
• Community service time off
• International Women's Day – March 8 is an official holiday for all employees
• Life and Medical Insurance