Principal Applied AI Engineer

VettedBench; India; Presencial; INR 4.000.000 - 7.000.000; Jornada completa

Descripción de la vacante

VettedBench is seeking a Principal Software Engineer to lead the design and delivery of complex AI and agentic capabilities across its product portfolio. This is a hands-on role with ownership of significant systems and platform components, solving ambiguous problems and setting reliability and evaluation standards.

You will collaborate with Product, Architecture, Security, Data, and Operations teams to translate business needs into durable platform solutions, build reusable frameworks, and

Formación

• 12+ years of professional software engineering experience, including ownership of production systems.
• Advanced programming skills in Python, Java, or another relevant production language.
• Strong experience building distributed systems, APIs, integrations, cloud services, and production-grade applications.
• Hands-on experience delivering generative AI or agentic systems into production.
• Experience with agent orchestration, tool calling, retrieval-augmented generation, prompt management, or model integration.
• Experience implementing AI evaluation, tracing, monitoring, security controls, and reliability mechanisms.
• Strong understanding of software architecture, automated testing, CI/CD, cloud deployment, and production operations.
• Ability to lead complex technical work while remaining hands-on.
• Strong technical judgement and clear written and verbal communication.

Responsabilidades

• Design and deliver complex services, agentic workflows, and shared AI platform capabilities.
• Build multi-step agentic systems that combine reasoning, tool use, retrieval, memory, policy controls, and human oversight.
• Establish robust approaches for AI evaluation, observability, model selection, fallback behaviour, and failure recovery.
• Lead technical delivery across multiple contributors and coordinate dependencies with product and platform teams.
• Review designs and code for scalability, security, performance, reliability, maintainability, and cost.
• Resolve complex production issues and implement corrective actions that prevent recurrence.
• Create reusable frameworks, reference implementations, and engineering standards that accelerate development.
• Partner with Product, Architecture, Security, Data, and Operations teams to translate business problems into durable platform solutions.
• Evaluate emerging AI technologies and recommend adoption based on technical evidence, enterprise requirements, and business value.
• Contribute directly to implementation while influencing important architectural and engineering decisions.

Conocimientos

12+ years experience

Python/Java

Distributed systems

Generative AI

Agent orchestration

AI evaluation/observability

Software architecture

Hands-on leadership

Communication

Herramientas

Kubernetes

Docker

LangGraph

AutoGen

Semantic Kernel

Descripción del empleo

About The team

The team Software helps the world's largest enterprises automate mission-critical business processes. Our platforms support complex enterprise workloads across ERP systems, business applications, cloud infrastructure, and on-premises environments.

The team is building reusable AI infrastructure, agentic capabilities, developer tools, and platform services that enable enterprise-ready AI features across its product portfolio.

Role Mission

As a Principal Software Engineer, you will lead the design and delivery of complex, production-grade AI and agentic capabilities that can be reused across The team products.

You will solve ambiguous engineering problems, establish standards for reliability and AI evaluation, and contribute to important technical decisions. This is a hands-on role with ownership of significant systems and platform capabilities.

Key Responsibilities

• Design and deliver complex services, agentic workflows, and shared AI platform capabilities.
• Build multi-step agentic systems that combine reasoning, tool use, retrieval, memory, policy controls, and human oversight.
• Establish robust approaches for AI evaluation, observability, model selection, fallback behaviour, and failure recovery.
• Lead technical delivery across multiple contributors and coordinate dependencies with product and platform teams.
• Review designs and code for scalability, security, performance, reliability, maintainability, and cost.
• Resolve complex production issues and implement corrective actions that prevent recurrence.
• Create reusable frameworks, reference implementations, and engineering standards that accelerate development.
• Partner with Product, Architecture, Security, Data, and Operations teams to translate business problems into durable platform solutions.
• Evaluate emerging AI technologies and recommend adoption based on technical evidence, enterprise requirements, and business value.
• Contribute directly to implementation while influencing important architectural and engineering decisions.

Scope and Expected Impact

• Own complex systems or platform capabilities that affect the immediate team and multiple partner teams.
• Operate independently when requirements, risks, or implementation approaches are not fully defined.
• Influence technical direction through architecture, working software, design reviews, and measurable outcomes.
• Drive improvements that reduce technical and operational risks across multiple services or product areas.
• Lead the technical execution of initiatives involving multiple contributors and cross-functional stakeholders.
• Balance short-term delivery requirements with long-term platform maintainability and scalability.

Must Have Qualifications

• 12+ years of professional software engineering experience, including ownership of production systems.
• Advanced programming skills in Python, Java, or another relevant production language.
• Strong experience building distributed systems, APIs, integrations, cloud services, and production-grade applications.
• Hands-on experience delivering generative AI or agentic systems into production.
• Experience with agent orchestration, tool calling, retrieval-augmented generation, prompt management, or model integration.
• Experience implementing AI evaluation, tracing, monitoring, security controls, and reliability mechanisms.
• Strong understanding of software architecture, automated testing, CI/CD, cloud deployment, and production operations.
• Ability to lead complex technical work while remaining hands-on.
• Strong technical judgement and clear written and verbal communication.

Strong Plus

• Experience with LangGraph, AutoGen, Semantic Kernel, or custom agent orchestration frameworks.
• Working knowledge of transformer architectures, model fine-tuning, inference strategies, or model evaluation.
• Experience with vector databases, model gateways, prompt lifecycle platforms, or AI observability tools.
• Experience with Kubernetes, Docker, messaging systems, event-driven architectures, or distributed systems.
• Experience in enterprise middleware, workflow orchestration, ERP, or integration platforms.
• Experience building internal platforms, developer tools, or reusable capabilities used across engineering teams.
• Exposure to regulated, security-sensitive, or high-availability enterprise environments.

What Success Looks Like

• Delivers significant AI systems or platform capabilities with measurable adoption and operational reliability.
• Creates reusable engineering patterns that can be adopted across multiple teams.
• Improves technical decisions by clearly documenting trade-offs and validating them with evidence.
• Leads complex initiatives from technical design through production deployment and operational ownership.
• Maintains strong individual technical contribution while influencing broader engineering outcomes.
• Becomes a trusted technical contributor across the AI and Agentic Engineering organization.

*If you like growth and working with happy, enthusiastic over-achievers, you'll enjoy your career with us!*

**THE LEGAL BIT**

The team is an equal opportunity employer. The team prohibits unlawful discrimination based on race, colour, religion, sex, gender identity, marital or veteran status, age, national origin, ancestry, citizenship, physical or mental disability, medical condition, genetic information or characteristics (or those of a family member), sexual orientation, pregnancy or any other consideration made unlawful by regional or local laws. We also prohibit discrimination based on a perception that anyone has any of those characteristics or is associated with a person who has or is perceived as having any of those characteristics. All such discrimination is unlawful and will have a zero tolerance policy applied to it.

The team will comply with all local data protection laws, including GDPR when it comes to the h