SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Cornerstone is seeking a Senior Principal AI Engineer to design, develop, and deploy production-grade AI agents and multi-agent systems using modern LLM frameworks. You will build and optimize Retrieval-Augmented Generation (RAG) solutions for enterprise-scale applications, developing intelligent workflows involving planning, reasoning, memory management, tool calling, and function calling.
Key responsibilities include designing and implementing scalable backend services and REST APIs using Python frameworks such as FastAPI, integrating LLMs with enterprise systems, vector databases, APIs, and external tools. You will deploy AI applications using Docker, Kubernetes, and cloud platforms (AWS, Azure, GCP), and optimize systems for latency, scalability, reliability, and cost efficiency.
You will build evaluation pipelines to measure retrieval quality, response relevance, hallucination rates, and overall LLM performance. This includes implementing semantic search, hybrid search, reranking, embedding pipelines, and vector database integrations. You'll establish observability, monitoring, logging, and tracing for AI applications using industry-standard tools.
Collaboration is central to the role—you will work with product managers, software engineers, data scientists, and platform teams to deliver end-to-end AI solutions. You will mentor junior engineers and promote AI engineering best practices, coding standards, and architectural excellence. Staying current with emerging advancements in LLMs, Agentic AI, RAG, and AI infrastructure is expected.
Required qualifications: Bachelor's or master's degree in computer science, AI, machine learning, or related technical field. 8+ years of overall software engineering experience, with minimum 3 years building AI/Generative AI applications using LLMs and 3+ years developing scalable backend software and distributed systems. Strong proficiency in Java and Python, hands-on experience with AI orchestration frameworks (LangGraph, LangChain, LlamaIndex), and production-grade RAG system design. Experience with vector databases (Milvus, Pinecone, Weaviate, OpenSearch, Elasticsearch, FAISS, ChromaDB) and integrating LLMs (OpenAI GPT, Claude, Gemini, Llama, Mistral, Amazon Nova, Azure OpenAI). Strong REST API development skills using FastAPI, containerization/orchestration (Docker, Kubernetes), cloud deployment, CI/CD pipelines, and AI evaluation/monitoring tools (LangSmith, Langfuse, MLflow, OpenTelemetry, Prometheus, Grafana). Excellent problem-solving, communication, and cross-functional collaboration skills required.
