Staff AI Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Staff AI Engineer based in United States. As a Staff AI Engineer, you will shape the technical direction of advanced AI products and help turn ambitious ideas into dependable production systems. You will work across generative AI, enterprise RAG, agentic workflows, machine learning pipelines, and AI infrastructure. The role combines hands-on engineering with broad technical leadership and cross-team influence. You will tackle complex, ambiguous challenges while building scalable foundations that other engineers can leverage. You will collaborate closely with Product, Engineering, Data Science, Data Engineering, and Analytics teams. Your work will directly influence the quality, reliability, security, and customer impact of conversational and analytical AI experiences.

Accountabilities

• Shape the technical direction of AI products by translating product goals into clear architecture, priorities, technical decisions, and delivery plans.
• Lead architectural decisions across AI-assisted experiences, adaptive conversations, research synthesis, and other AI-powered capabilities.
• Own complex engineering initiatives from problem definition and experimentation through production deployment and ongoing operation.
• Design and build generative AI applications using large language models, RAG, vector search, tool use, and agentic systems.
• Develop reusable AI services and APIs while establishing scalable patterns for data flows, model orchestration, retrieval, and structured and unstructured data.
• Guide machine learning infrastructure using Python, Docker, Kubernetes, AWS, Terraform, CI/CD, and related cloud technologies.
• Build reliable batch and real-time processing pipelines using technologies such as Kafka and Airflow.
• Establish effective approaches for experimentation, model versioning, registries, deployments, and machine learning lifecycle management.
• Define evaluation strategies and release criteria covering accuracy, relevance, reliability, fairness, latency, security, and cost.
• Improve retrieval quality through techniques such as chunking, embeddings, context selection, and reranking, while connecting offline evaluation with production monitoring and customer feedback.
• Build safeguards for security, privacy, responsible AI, prompt injection, data leakage, and unexpected model behavior into system architecture.
• Establish engineering standards for testing, observability, incident response, deployment, security, and AI system operations.
• Mentor engineers and technical leads while helping teams make well-reasoned technical trade-offs without relying on formal authority.
• Evaluate emerging AI research, tools, and technologies and identify opportunities where they can deliver practical value.
• Partner with Product and Engineering teams to prioritize AI investments based on customer needs, technical feasibility, and measurable business impact.
• Communicate technical concepts, risks, dependencies, and trade-offs clearly to both technical and nontechnical stakeholders.

Requirements

• Significant experience building and operating machine learning or AI systems in production, with demonstrated technical leadership beyond individual projects.
• Proven experience leading complex, cross-functional engineering initiatives from ambiguous requirements through measurable production outcomes.
• Strong Python and software engineering skills, with the ability to contribute directly to production systems.
• Experience designing production services and APIs using technologies such as FastAPI.
• Hands-on experience developing generative AI applications using large language models, RAG, tool use, agentic systems, or comparable approaches.
• Strong understanding of enterprise RAG architecture, including retrieval, chunking, embeddings, reranking, evaluation, and monitoring.
• Experience defining AI evaluation methodologies and using evidence to guide model, architecture, and release decisions.
• Experience with frameworks such as PyTorch, LangChain, LangGraph, or similar technologies.
• Strong experience designing and operating cloud environments using AWS, Docker, Kubernetes, Terraform, and CI/CD practices.
• Familiarity with AWS services such as SageMaker or Bedrock.
• Experience with event-driven processing, vector databases, and machine learning lifecycle technologie…