Agentic AI Platform (Full Stack)

We are looking for a strong hands-on Senior Data Engineer to help build and scale a production-grade Agentic AI Platform on ACP (Airtel Sovereign Cloud Platform). This role is ideal for engineers who have worked on high-scale systems, have contributed to platform engineering, and want to deepen their exposure to LLM and Agentic AI systems. You will work across data platforms, distributed systems, and AI infrastructure, contributing to sovereign, open, and future-ready cloud services.

Responsibilities & Accountabilities

Design and build core components of the Agentic AI platform (agent workflows, memory, tool

integration, execution runtime).

Develop and operate scalable data pipelines supporting LLMs and AI agents.

Contribute to building platform abstractions for multi-tenant, secure agent execution.

Integrate LLMs, vector stores, and enterprise data sources into reliable systems.

Participate in architecture, design, and code reviews for platform services.

Own features across the full SDLC: design, development, testing, deployment, and production

support.

Collaborate with infra, platform, and AI teams to evolve ACPs AI and data PaaS offerings.

Follow open-source-first and cloud-native engineering practices.

Required Skills & Experience

68 years of experience in backend or data engineering.

Strong hands-on experience building scalable distributed systems.

Proficiency in Java (preferred) or other backend languages (Python, Scala, Go).

Solid fundamentals in:

o Data engineering (batch & streaming pipelines)

o Distributed systems and microservices

o APIs, messaging, and event-driven architectures

Practical exposure to LLMs and AI-driven systems.

Experience across end-to-end SDLC, including CI/CD and production operations.

Strong problem-solving and system design skills.

Good to Have

Exposure to Agentic AI concepts or frameworks (LangChain, LangGraph, LlamaIndex, AutoGen, etc.).

Experience with public cloud platforms (AWS, GCP, Azure).

Knowledge of vector databases, embeddings, and retrieval pipelines.

Experience with Kubernetes and cloud-native stacks.

Prior work on data platforms, AI platforms, or internal PaaS.