About the role
Team: Engineering
Location: Chennai / Remote
Manager: SVP of Engineering
Shift: IST
Employment Type: Full Time
Job SummaryWe are looking for a Senior AI Engineer to design and build the foundational AI powering the next generation of .
This is a hands-on architecture and engineering role. You will own the core AI platform, including agent orchestration, tool execution, authorization, durable workflows, evaluation, and observability, working closely with Engineering, Product, Data Science, DevOps, and Security teams.
Primary ResponsibilitiesAI Platform & Agentic Architecture- Design and build the core platform for AI agents, skills, orchestration, and agentic applications.
- Build reusable capabilities for state management, task routing, tool execution, workflow orchestration, and recovery.
- Define architecture standards for how AI agents securely interact with services and enterprise systems.
- Design authentication, authorization, RBAC, policy enforcement, and multi-tenant isolation for AI agents and their capabilities.
- Build reliable execution with durable workflows, retries, failure recovery, approvals, auditability, and observability.
- Establish evaluation and monitoring practices to ensure AI systems are reliable, secure, and production-ready.
- Build secure integrations between agents, MCP/tools, APIs, skills, and domain capabilities.
- Develop scalable, cloud-native and event-driven platform services using Python, APIs, Kafka, Kubernetes, and AWS/GCP.
- Integrate AI capabilities with 's existing services, data platforms, and infrastructure.
- Own the architecture and hands-on implementation of major AI platform initiatives.
- Partner with the Senior Solution Architect to define how the AI platform integrates with core XMP services.
- Establish reusable engineering standards and mentor engineers building AI capabilities.
- Evaluate emerging AI technologies and drive their practical adoption across the platform.
- 8+ years of software engineering experience building production systems.
- Strong experience designing and building distributed, cloud-based systems and microservices on AWS and/or GCP.
- Experience with event-driven architectures and technologies such as Kafka.
- Strong proficiency in Python, building production-grade APIs and backend services.
- 3+ years building production AI/ML systems, including at least 2 years shipping LLM-based or agentic systems to production.
- Hands-on experience building AI agents and stateful, multi-step agentic workflows using orchestration frameworks.
- Hands-on experience building AI agents and agentic workflows.
- Experience with tool calling and function calling.
- Experience with MCP or equivalent tool integration protocols.
- Experience with RAG, embeddings, vector search, or knowledge-based AI systems.
- Experience with LLM evaluation and AI observability.
- Experience managing LLM cost and latency, including token budgets, caching, and model selection trade-offs.
Strong understanding or hands-on experience with:
- Authentication and authorization (OAuth / JWT)
- Multi-tenant isolation
- Audit logging
- Securing agentic systems against prompt injection, excessive tool permissions, and sensitive-data leakage
- Securing agentic systems against prompt injection, excessive tool permissions, and leakage of PII or customer data
- Experience designing and documenting large-scale system architectures.
- Strong understanding of distributed systems and cloud architecture.
- Ability to define clear boundaries between AI agents, platform services, domain capabilities, and authoritative business logic.
- Ability to design systems that remain deterministic and secure around inherently probabilistic AI components.
- Experience making architecture and technology decisions based on scalability, reliability, security, and business requirements.
- Experience with Temporal, LangGraph, LangChain, OpenAI Agents SDK, Google ADK, Semantic Kernel, or equivalent orchestration frameworks.
- Experience building MCP servers and clients.
- Experience with graph databases such as Neo4j.
- Experience with Elasticsearch/OpenSearch, Redis, and BigQuery or similar large-scale data platforms.
- Experience working with financial, healthcare, or other security-sensitive systems.Experience with Docker and Kubernetes.
- Experience with distributed tracing (OpenTelemetry), circuit breakers, and model routing/fallback strategies.
We believe that experience is everything. has built the Experience Management Platform (XMP) to help organizations drive operational and behavioral change during the moments that matter.
XMP delivers business outcomes including increased customer satisfaction, brand loyalty, online reputation and visibility, employee engagement, and compliance — making every experience matter more.