AI Delivery Engineer - AWS Bedrock

Kunai

3d•$135,000 - $220,000

About The Position

Kunai builds full-stack technology solutions for financial services organizations and their customers. This client-facing Generative AI role works with multidisciplinary delivery pods to translate business problems into AI applications, from discovery and prototyping through production release and handoff to client engineers. Approximately 70% of the role focuses on building with Amazon Bedrock and related AWS services, while the remainder involves working directly with client users and technical teams. The position may align to Senior Engineer or Staff Engineer; compensation varies by level and depends on skills, experience, qualifications, location, and applicable employment laws. The role includes substantial client travel, primarily Monday through Thursday. The posting gives travel expectations of up to 70% in the requirements and 80% in a later disclaimer. The successful candidate will help clients modernize and adopt emerging technology, delivering solutions that satisfy agreed standards for quality, safety, latency, reliability, and cost. They will also contribute reusable engineering assets, support technical pursuits, and enable client teams to operate and maintain delivered solutions.

Requirements

At least 4 years of experience building and deploying production software.
At least 3 years of experience writing Python in production.
At least 3 years of experience building on AWS, including AWS Lambda and AWS IAM.
At least 1 year of experience building applications that use LLMs, including retrieval, structured outputs, tool calling, or agent workflows.
Experience working directly with clients or business stakeholders to clarify requirements and demonstrate progress.
Experience with version control, automated testing, and deployment pipelines.
Ability to travel up to 70%, typically Monday through Thursday, including on-site client work; a later disclaimer states expected travel is 80%, mostly Monday through Thursday.
Bachelor’s degree in computer science, engineering, or a related field, or equivalent practical experience. The posting also specifies a minimum bachelor’s degree, with an alternative requiring three years of specialized training and/or progressively responsible technology work for each missing year of college.
Applicants must not require PwC sponsorship through the H-1B lottery, now or in the future, subject to the policy linked in the posting.

Nice To Haves

Delivery experience with Amazon Bedrock, Bedrock AgentCore, Bedrock Knowledge Bases, Bedrock Guardrails, or Amazon SageMaker.
Experience building at least one production application on AWS that calls a foundation model through Amazon Bedrock or another model API.
Experience building evaluation datasets, adversarial tests, or AI observability for a production system.
Experience with enterprise search, document processing, or structured and unstructured data pipelines.
Experience building tools or integrations using APIs or Model Context Protocol.
Proficiency in a second language such as TypeScript, Java, or Go.
AWS certifications such as Solutions Architect – Professional or Associate, or Certified Generative AI Developer.
Experience in financial services, consumer markets, or technology, media, and telecommunications.
Experience mentoring engineers.

Responsibilities

Map client workflows with business users and process owners; define use cases, delivery backlogs, and measurable acceptance criteria.
Build working prototypes early and test them using representative client data and user feedback.
Develop agent workflows, retrieval and grounding, tool calling, and APIs using Python, Amazon Bedrock, Bedrock AgentCore, and Bedrock Knowledge Bases.
Integrate AI solutions with client systems using AWS Lambda, Amazon SageMaker, and approved data sources, with authentication and permission-aware access through AWS IAM.
Write automated tests and AI evaluations, and build deployment pipelines, monitoring, and error handling.
Assess solutions against agreed release criteria for quality, safety, latency, reliability, and cost.
Configure Amazon Bedrock Guardrails and work with security, privacy, and risk specialists to translate requirements into technical controls, audit evidence, and human review steps.
Co-build with client engineers and provide documentation, runbooks, and knowledge transfer so client teams can operate the solution.
Contribute reusable components, evaluation assets, and implementation patterns to PwC’s engineering community while observing client confidentiality and IP obligations.
Support pursuits through technical demonstrations, feasibility assessments, and delivery estimates.