Artificial Intelligence Engineer

Provoke Solutions; United States; Remote; USD 83,000 - 165,000; Full time

Job summary

Provoke Solutions is hiring an AI Engineer to design, develop, and deploy AI-powered applications in a remote US setting. You will integrate LLMs from Bedrock, OpenAI, and Anthropic, building agentic workflows and secure, scalable solutions that fit enterprise needs.

The role emphasizes production‑ready code, continuous improvement, and collaboration with cross‑functional teams to solve real business problems using AI across cloud-native architectures.

Qualifications

• Bachelor's degree or equivalent practical experience in a relevant field.
• AWS Generative AI Developer or ML Engineer certification preferred.
• 2+ years of experience in business processes, automation, or AI.
• Hands-on experience designing agentic AI workflows in an enterprise environment.
• Ability to evaluate tools and implementation approaches for complex processes.
• Experience building business cases that quantify improvements and cost savings.

Responsibilities

• Design, develop, and deploy AI-powered applications using Python and modern AI tech.
• Integrate LLMs from Bedrock, OpenAI, and Anthropic into business workflows.
• Build agentic AI workflows with automated, multi-step reasoning and actions.
• Develop cloud-native AI services on AWS and serverless architectures.
• Implement retrieval-augmented generation and secure data handling.
• Test, monitor, and optimize AI applications for reliability and cost efficiency.

Skills

Python

AI Engineering

AWS

LLM Integration

Automation

Education

Bachelor's degree in Computer Science or related field

AWS Certified Generative AI Developer – Professional or MLA-C02

Tools

AWS

Bedrock API/SDK

OpenAI API

Anthropic API

Job description

Provoke Solutions is advancing the development and adoption of AI-powered solutions that improve workflows, automate complex tasks, and create new opportunities across the organization.

Overview

As an AI Engineer, you will help design, develop, integrate, and deploy AI-powered applications, including solutions that leverage large language models (LLMs), AI agents, and intelligent automation. Working alongside experienced engineers and cross-functional teams, you'll turn business and technical requirements into practical AI solutions that are secure, scalable, and reliable.

This is a hands‑on engineering role for someone who enjoys experimenting with emerging AI technologies, developing production‑ready applications, and integrating AI capabilities into existing systems and workflow.

Key Responsibilities

AI Application Development

• Design, build, and maintain AI-powered applications using Python and modern AI technologies.
• Integrate large language models from platforms such as Amazon Bedrock, OpenAI, and Anthropic into business applications and engineering workflows.
• Develop solutions that combine LLMs, APIs, data sources, and existing enterprise systems to solve practical problems.
• Evaluate AI models, tools, and frameworks to determine the best approach for specific use cases.

Agentic AI and Intelligent Automation

• Develop AI agents and multi‑step workflows that can reason, retrieve information, use approved tools, and execute defined tasks.
• Integrate agent capabilities with APIs, enterprise data sources, and internal applications.
• Build reusable components that support workflow automation and agent‑based applications.
• Test and refine agent behavior to improve accuracy, reliability, and consistency.

Cloud Engineering and Integration

• Develop and deploy AI services using AWS and cloud‑native technologies.
• Build serverless applications and event‑driven services using AWS Lambda, API Gateway, SQS, and related services.
• Work with Amazon Bedrock capabilities, including Agents, Knowledge Bases, and Guardrails, where appropriate.
• Integrate AI applications into existing software systems, APIs, and CI/CD workflows.

Data, Retrieval, and Context Management

• Implement retrieval‑augmented generation (RAG) solutions that allow AI applications to work with relevant enterprise information.
• Integrate document repositories, databases, APIs, and other data sources into AI‑powered workflows.
• Apply effective context management, retrieval strategies, and prompt design to improve the quality of model responses.
• Evaluate outputs for relevance, accuracy, and consistency.

Security, Testing, and Reliability

• Implement appropriate safeguards to reduce hallucinations, prompt injection risks, and unintended exposure of sensitive information.
• Apply secure coding practices, access controls, input validation, and appropriate secrets management.
• Develop automated tests and evaluation methods to assess AI application performance.
• Troubleshoot issues across application logic, model interactions, integrations, and cloud infrastructure.

Monitoring and Optimization

• Implement logging, metrics, and monitoring to understand application behavior and identify issues.
• Evaluate model performance, response quality, latency, and token consumption.
• Identify opportunities to improve efficiency, manage inference costs, and optimize application performance.
• Document technical implementations and contribute to continuous improvement across the AI engineering team.

Required Skills & Experience

• Bachelor's degree in Business, Computer Science, Engineering, or a related field, or equivalent practical experience.
• AWS Certified Generative AI Developer – Professional (AIP-C01) or AWS Certified Machine Learning Engineer - Associate (MLA-C02)
• Typically 2+ years of experience in business process analysis, process improvement, business transformation, intelligent automation, or a related discipline.
• Hands‑on experience designing and implementing agentic AI workflows or intelligent automation solutions in an enterprise environment.
• Demonstrated ability to evaluate complex business processes and independently determine appropriate solutions, tools, and implementation approaches.
• Experience developing business cases that quantify process improvements, operational efficiencies, cost savings, or other measurable business outcomes.
• Proficiency with AI tools, agentic platforms, and automation technologies, with the ability to evaluate emerging capabilities and adapt implementation strategies.
• Strong analytical and problem‑solving skills, including the ability to identify dependencies, anticipate risks, and evaluate multiple solution options.
• Proven ability to collaborate with technical and non‑technical stakeholders across multiple business functions.
• Experience developing new processes, procedures, or frameworks in environments where established practices or precedents may not exist.
• Strong communication skills, including the ability to translate complex technical concepts into clear business recommendations.

Desirable Qualifications

• 2-5 years of professional software engineering or relevant AI application development experience.
• Strong Python programming skills and experience developing maintainable, production‑quality applications.
• Hands‑on experience integrating LLM APIs, such as Amazon Bedrock, OpenAI, Anthropic, or comparable platforms.
• Understanding of generative AI concepts, including prompt engineering, model selection, context management, and output evaluation.
• Experience building API integrations and connecting applications to external services or enterprise systems.
• Familiarity with cloud platforms, preferably AWS, including services such as Lambda, API Gateway, IAM, and CloudWatch.
• Understanding of AI application security, including sensitive‑data protection, access controls, and common LLM vulnerabilities.
• Experience testing, debugging, and monitoring software applications.
• Familiarity with Git, version control, and collaborative software development practices.
• Ability to translate technical requirements into functional solutions and work effectively within a cross‑functional engineering team.

Working Hours

US time zone alignment. Flexibility to accommodate client schedules is part of the role.

Location

Remote (United States)

Role Type & Work Authorization

This role is offered as W2 hourly employment. Candidates must be authorized to work in the U.S. without VISA sponsorship.