Staff Engineer / AI Builder

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Staff Engineer / AI Builder based in the United States.

Join an innovative technology environment focused on designing and delivering advanced AI solutions that solve real-world business challenges. As a Staff Engineer / AI Builder, you will take technical ownership of the architecture, development, and deployment of production-grade AI and machine learning systems. You will lead the development of agentic workflows, generative AI applications, and scalable infrastructure, ensuring reliability, security, and performance. Working across backend, frontend, and cloud environments, you will transform complex technical requirements into practical solutions that create measurable value for clients. You will also play a key role in establishing engineering standards, mentoring colleagues, and influencing architectural decisions. This is an exciting opportunity to shape the future of enterprise AI through hands-on engineering, technical leadership, and close collaboration with multidisciplinary teams.

Accountabilities:

Agentic AI and Generative AI Engineering:
Design, develop, and maintain sophisticated agentic workflows, including reasoning loops, tool and function calling, and orchestration across single-agent and multi-agent architectures.
Select appropriate architectural patterns based on business requirements, technical complexity, scalability, and performance considerations.
Build and optimize Retrieval-Augmented Generation (RAG) pipelines, including document chunking, embeddings, vector search, re-ranking, and knowledge source refresh mechanisms.
Develop and integrate AI solutions using AWS Bedrock and Agent Core, including Model Context Protocol (MCP)-based tools and integrations.
Design and maintain production-ready system prompts with structured instructions, output constraints, and few-shot examples.
Implement comprehensive evaluation and observability frameworks using golden datasets, RAGAS-style metrics, LLM-as-judge techniques, and tracing tools such as LangFuse or LangSmith.
Build resilient AI systems capable of handling model failures and service degradation through retries, backoff strategies, circuit breakers, fallback models, and appropriate error handling.
Full-Stack and Platform Engineering:
Develop scalable backend services and RESTful APIs using Python and Node.js, including serverless solutions built with AWS Lambda and API Gateway.
Design and manage DynamoDB single-table data models, including composite keys and transactional operations for conversation state, agent memory, and session history.
Implement event-driven architectures and asynchronous workflows using AWS Step Functions, SQS, and EventBridge.
Contribute to frontend integrations to ensure AI-powered features are seamlessly delivered to end users.
Write clean, maintainable, and well-tested code across the technology stack.
Support cloud-native deployments, monitoring, troubleshooting, and production maintenance using AWS and Docker.
Ensure applications meet high standards of reliability, scalability, security, and operational performance.
Technical Leadership and Collaboration:
Lead architectural discussions and provide informed technical recommendations, clearly evaluating trade-offs between different engineering approaches.
Partner with Product, Design, and Delivery teams across global environments to define requirements, scope projects, and deliver end-to-end solutions.
Mentor engineers and help establish best practices for agentic AI development and AI-assisted engineering tools such as Claude Code.
Take full ownership of assigned features and releases, from initial design and implementation through debugging, optimization, deployment, and ongoing maintenance.
Contribute to engineering standards and technical strategies that support the long-term scalability and evolution of AI systems.
Promote a culture of technical excellence, accountability, collaboration, and continuous improvement.
Requirements:
At least 6 years of professional software engineering experience, including substantial hands-on experience developing and deploying generative AI or LLM-powered systems in production environments.
Strong practical expertise in agentic AI engineering, including reasoning loops, tool and function calling, and single-agent and multi-agent orchestration architectures.
Ability to evaluate architectural approaches and explain when single-agent systems are more appropriate than multi-agent solutions.
In-depth knowledge of RAG architectures, including document chunking strategies, embeddings, vector databases, OpenSearch or equivalent technologies, cosine similarity search, and re-ranking techniques.
Experience building evaluation and observability frameworks for LLM applications, including golden datasets, LLM-as-judge methodologies, RAGAS or comparable evaluation metrics, and tracing platforms such as LangFuse or LangSmith.
Advanced prompt engineering capabilities, with experience designing structured, production-ready system prompts that include clear instructions, constraints, and output requirements.
Hands-on experience with the AWS generative AI ecosystem, particularly Bedrock, Agent Core, Lambda, DynamoDB, S3, SQS, EventBridge, and Step Functions.
Strong programming skills in Python and Node.js, with experience developing backend services, full-stack applications, and RESTful APIs.
Solid understanding of production reliability and resilience patterns for AI-powered systems, including retry mechanisms, exponential backoff, circuit breakers, and fallback model strategies.
Experience with Docker, containerization, and cloud-native application deployment.
Ability to independently manage complex, ambiguous, and integration-heavy engineering challenges, taking ownership from initial problem definition through production delivery.
Strong analytical and problem-solving skills, combined with the ability to communicate complex technical decisions and justify architectural recommendations.
Demonstrated technical leadership, mentoring capabilities, and the ability to collaborate effectively with multidisciplinary and distributed teams.
Nice to Have:
Direct experience with Amazon Bedrock Agent Core, including agent registration, MCP tool integration, memory and session management, and gateway provisioning.
Previous experience working in regulated or high-stakes industries such as healthcare, financial services, or education, where system reliability, security, and evaluation rigor are essential.
Familiarity with workflow orchestration platforms such as AWS Step Functions, Sequencer, or similar state-machine-based technologies.
Practical experience implementing and operating LLM observability tools in production environments.
Experience delivering enterprise-grade AI solutions that integrate with complex business systems and operational workflows.
Benefits:
Competitive Compensation: Annual salary ranging from $165,604 to $228,491 USD, depending on qualifications, experience, skills, seniority, geographic location, and other relevant factors.
Comprehensive Healthcare: Medical, dental, and vision insurance for eligible employees.
Retirement Savings: Access to a 401(k) retirement savings plan for eligible employees.
Paid Time Off: Paid leave to support personal needs, rest, and work-life balance.
Professional Development: Opportunities to work on advanced AI technologies and solve challenging enterprise engineering problems.
Technical Ownership: Significant autonomy and responsibility in shaping AI architecture, engineering standards, and production systems.
Collaborative Environment: Work alongside multidisciplinary teams in an innovation-driven environment focused on creativity, technical excellence, and measurable client impact.
Career Growth: Opportunities to strengthen technical leadership skills, mentor other engineers, and influence the evolution of enterprise AI solutions.