Conversational AI Platform Engineer

Cognizant; Austin (TX); Remote; USD 84,000 - 130,000; Full time

Benefits offered by this job

Medical/Dental/Vision/Life Insurance

Paid holidays plus Paid Time Off

401(k) plan and contributions

Long-term/Short-term Disability

Paid Parental Leave

Employee Stock Purchase Plan

Job summary

Cognizant is seeking a Conversational AI Platform Engineer to design, develop, and deploy enterprise-grade conversational AI solutions, voice and chat bots, and agentic AI applications powered by AWS services and LLMs. You will collaborate with AI Engineering, architects, product owners, and business stakeholders to deliver scalable AI-driven experiences.

Responsibilities include building platforms with AWS Lex, Bedrock and agent orchestration, implementing prompt engineering, NLU, and ongoing

Qualifications

• Strong hands-on experience developing Conversational AI and Agentic AI platforms using Amazon Bedrock, Bedrock AgentCore, AWS Lex, AWS Strands SDK/Framework, and related AWS AI services.
• Hands-on experience building production-grade Generative AI solutions using Amazon Bedrock, including LLM application development, agent workflows, tool calling, and function calling.
• Strong experience designing and developing voice bot and chat bot solutions, including intent modeling, conversation design, prompt engineering, and NLU concepts.
• Strong AWS cloud development experience including AWS Lambda, Amazon S3, DynamoDB, API Gateway, IAM, and CloudWatch.
• Experience securing enterprise AI applications through guardrails, prompt injection mitigation, data protection, access controls, responsible AI controls, and AI security best practices.
• Experience monitoring, troubleshooting, and optimizing AI agents and conversational AI platforms in production environments.
• Hands-on experience with conversational analytics, agent evaluation frameworks, and bot performance optimization.
• Experience using at least one AI-assisted development platform such as GitHub Copilot, ChatGPT, Cursor, Claude, or a similar development accelerator.

Responsibilities

• Design, develop, and deploy conversational AI platforms, including voice bots and chat bots, using AWS Lex and other deterministic bot technologies.
• Build and orchestrate Agentic AI applications leveraging Amazon Bedrock, Bedrock AgentCore, and AWS Strands SDK/Framework.
• Develop production-grade Generative AI and LLM-based applications utilizing tool calling, function calling, multi-agent workflows, and agent orchestration patterns.
• Design intent models, conversation flows, prompts, and Natural Language Understanding (NLU) capabilities to deliver highly effective user experiences.
• Monitor, optimize, troubleshoot, and continuously improve AI agents and conversational systems for accuracy, latency, scalability, reliability, observability, and cost efficiency.

Skills

Conversational AI platforms

AWS Lex

Bedrock

LLMs

Agent orchestration

Prompt engineering

NLU concepts

AWS Lambda/S3/DynamoDB/API Gateway

Security in enterprise AI

Tools

Bedrock AgentCore

AWS Strands SDK

AWS Lambda

DynamoDB

API Gateway

Job description

About the Role

As a Conversational AI Platform Engineer , you will make an impact by designing, developing, and deploying enterprise-grade conversational AI solutions, voice and chat bots, and agentic AI applications powered by AWS services and Large Language Models (LLMs). You will be a valued member of the AI Engineering team and work collaboratively with architects, cloud engineers, product owners, business stakeholders, and cross-functional technology teams to deliver innovative AI-driven solutions.

In this role, you will:

• Design, develop, and deploy conversational AI platforms, including voice bots and chat bots, using AWS Lex and other deterministic bot technologies.

• Build and orchestrate Agentic AI applications leveraging Amazon Bedrock, Bedrock AgentCore, and AWS Strands SDK/Framework.

• Develop production-grade Generative AI and LLM-based applications utilizing tool calling, function calling, multi-agent workflows, and agent orchestration patterns.

• Design intent models, conversation flows, prompts, and Natural Language Understanding (NLU) capabilities to deliver highly effective user experiences.

• Monitor, optimize, troubleshoot, and continuously improve AI agents and conversational systems for accuracy, latency, scalability, reliability, observability, and cost efficiency.

Work Model

We strive to provide flexibility wherever possible. Based on this role's business requirements, this is a remote position open to qualified applicants in the United States . Regardless of your working arrangement, we are here to support a healthy work-life balance through our various wellbeing programs.

What You Need to Have to Be Considered

• Strong hands-on experience developing Conversational AI and Agentic AI platforms using Amazon Bedrock, Bedrock AgentCore, AWS Lex, AWS Strands SDK/Framework, and related AWS AI services.

• Hands-on experience building production-grade Generative AI solutions using Amazon Bedrock, including LLM application development, agent workflows, tool calling, and function calling.

• Strong experience designing and developing voice bot and chat bot solutions, including intent modeling, conversation design, prompt engineering, and NLU concepts.

• Strong AWS cloud development experience including AWS Lambda, Amazon S3, DynamoDB, API Gateway, IAM, and CloudWatch.

• Experience securing enterprise AI applications through guardrails, prompt injection mitigation, data protection, access controls, responsible AI controls, and AI security best practices.

• Experience monitoring, troubleshooting, and optimizing AI agents and conversational AI platforms in production environments.

• Hands-on experience with conversational analytics, agent evaluation frameworks, and bot performance optimization.

• Experience using at least one AI-assisted development platform such as GitHub Copilot, ChatGPT, Cursor, Claude, or a similar development accelerator.

These Will Help You Stand Out

• Knowledge of secure AI/LLM deployment patterns and cloud-native agent architectures.

• Experience developing advanced multi-agent systems and complex agent orchestration patterns.

• Experience implementing Retrieval-Augmented Generation (RAG) architectures.

• AWS certifications such as AWS Certified AI Practitioner, AWS Certified AI Engineer, or equivalent.

• Experience implementing Responsible AI, AI governance, compliance, enterprise AI security controls, and model evaluation frameworks.

Applications will be accepted until: 10/30/2026

Please note, this role is not able to offer visa transfer or sponsorship now or in the future.

Salary and Other Compensation

The annual salary for this position is between $84,000pa - $130,000pa depending on experience and other qualifications of the successful candidate. This position is also eligible for Cognizant's discretionary annual incentive program, based on performance and subject to the terms of Cognizant's applicable plans.

Cognizant offers the following benefits for this position, subject to applicable eligibility requirements:

• Medical/Dental/Vision/Life Insurance

• Paid holidays plus Paid Time Off

• 401(k) plan and contributions

• Long-term/Short-term Disability

• Paid Parental Leave

• Employee Stock Purchase Plan

Disclaimer:

The salary, other compensation, and benefits information is accurate as of the date of this posting. Cognizant reserves the right to modify this information at any time, subject to applicable law.

Cognizant is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to sex, gender identity, sexual orientation, race, color, religion, national origin, disability, protected Veteran status, age, or any other characteristic protected by law.