Senior AI Engineer – Generative AI & Agentic AI

Senior AI Developer

About Principal: understand who we are

With more than 19,000 employees worldwide, Principal helps people and companies in Asia, Australia, Europe, Latin America, and North America build and protect their financial well-being. We’ve been doing this for 143 years. A FORTUNE 500 company, we’re known for our innovative ideas and real-life solutions that help customers make financial progress, no matter their income or portfolio size. Principal (India) is the global business services (GBS) for Principal Financial Group with 4000+ employees.

For more information, visit www.principal.com Follow us on Xcorp (previously Twitter), Facebook, LinkedIn, and YouTube.

Job Purpose: this section helps you understand the business and provides high level summary of the role

The Senior AI Agent Developer will design, build, test, deploy, and improve production-grade AI agents and agentic workflows that solve defined business problems. This is a senior hands-on developer role, not a solution architect position. The role will translate business requirements and technical designs into secure, maintainable software using large language models, retrieval-augmented generation, tool calling, APIs, MCP servers, and agent orchestration frameworks. The developer will work closely with product, process, data, platform, security, and engineering teams to deliver measurable business outcomes.

Essential Deliverables: the section helps understand the job ownership and accountability

· Design, build, and deploy AI agents, copilots, and agentic workflows leveraging enterprise AI platforms such as AWS AgentCore and MS Copilot Studio leveraging automation frameworks.

· Develop and orchestrate multi-agent solutions using modern orchestration frameworks, ensuring effective state management, routing, memory, tool selection, and human-in-the-loop controls.

· Design and implement Retrieval-Augmented Generation (RAG) solutions, including knowledge ingestion, embeddings, vector search, retrieval optimization, and source attribution.

· Integrate AI agents with enterprise applications, databases, knowledge repositories, APIs, and cloud services to enable end-to-end business workflows.

· Build and manage MCP-enabled integrations to securely expose enterprise tools, data, and services to AI agents.

· Implement robust tool calling, function execution, validation, security controls, and audit logging to ensure reliable agent operations.

· Develop reusable AI components, prompts, connectors, and frameworks while maintaining high standards of code quality, testing, and documentation.

· Conduct functional, performance, security, and responsible AI testing, ensuring solutions are resilient against hallucinations, prompt injection, data leakage, and misuse.

· Establish monitoring and observability mechanisms to track agent performance, adoption, quality, cost, and business outcomes.

· Collaborate with business stakeholders to translate requirements into scalable AI solutions and drive successful deployment and adoption.

Qualifications-Certifications-Relevant Work Experience:

Preferred educational background: Bachelor's degree in Computer Science, Engineering, Information Technology, or a related discipline. Equivalent relevant experience may be considered.

Total years of industry experience: 8–10 years of experience in software engineering, automation, data, or AI application development, with significant hands-on development expertise. Proven experience delivering AI/GenAI solutions from prototype through production deployment. Strong background in integrating AI solutions within enterprise platforms and governed, security-conscious environments. Demonstrated ability to collaborate effectively with business stakeholders, architects, data engineers, security teams, and platform teams while maintaining ownership of solution delivery. Excellent communication skills with the ability to articulate technical concepts, evaluate trade-offs, document solutions, and drive user adoption

Flexibility Option and Base Location

Principal offers modern hybrid working arrangements that allow all employees to adapt to changing work preferences.

Flexibility Option for the role: Hybrid, 3 days in office

Base Location: Pune, India

Principal is an Equal Opportunity Employer and considers applicants for all positions without regard to race, color, religion or belief, sex, age, national origin, citizenship status, marital status, military/veteran status, genetic information, sexual orientation, gender identity, physical or mental disability or any other characteristic protected by applicable laws. Principal is committed to creating a dynamic work environment that values diversity and inclusion, respect and integrity, customer focus, and innovation.

Principal reserves the right to change this job description any time, and this job description is not intended to detail every requirement of the job. Other job requirements may be found, for example, in an individual’s goals as determined by their leader.

Pay: ₹2,200,000.00 - ₹2,800,000.00 per year

Benefits:

• Cell phone reimbursement
• Flexible schedule
• Health insurance
• Internet reimbursement
• Leave encashment
• Life insurance
• Paid sick time
• Paid time off
• Provident Fund
• Work from home

Application Question(s):

• Are you 100% Sure that you have previously NOT applied at Tech Mahindra, either directly or through a consultant. vendor or employee
• What is your current location?
• The first round is virtual, but the final round is ONLY face-to-face at Pune. Proceed if you are 100% sure to attend f2f interview
• In how many days can you join? Please do not write "Serving Notice
• What is your CCTC?
• What is your ECTC (max 28 LPA)?
• Have you built and deployed production AI agents or agentic workflows using LLMs, with tool/function calling and measurable business outcomes?
• Have you implemented end-to-end RAG, including document ingestion, embeddings, vector search, retrieval tuning & source citations in a live solution?
• Which agent orchestration frameworks have you used for routing, state, memory, tool selection or multi-agent workflows in hands-on projects?
• Have you developed AI applications in Python and integrated agents with REST APIs, databases or enterprise systems?
• Have you implemented MCP servers/clients or used AWS AgentCore or Microsoft Copilot Studio to build enterprise AI agent integrations hands-on?
• How have you secured and monitored production AI agents against prompt injection, hallucinations and data leakage, including testing, logs and alerts?
• Please read the JD and also answer all questions.

Work Location: In person