Sr. Tech Lead - Global Network Services

Tata Communications Limited; Bengaluru; Hybrid; INR 1.800.000 - 3.000.000; Vollzeit

Zusammenfassung

Tata Communications Limited is seeking a Senior AI Engineer to build production-grade Agentic AI capabilities for the IZO+ MCN platform across AWS, Azure, GCP and OCI. This hybrid Bengaluru role blends AI/LLM engineering with backend development to enable network troubleshooting, automation and governance.

You will work with Product, Architecture, Engineering, QA, SRE and Security to deliver scalable AI services using Python, Java/Spring Boot or Go, Docker/Kubernetes and CI/CD.

Qualifikationen

• 5-8 years of professional software engineering experience.
• Strong Python development skills and FastAPI experience.
• Production experience in Java/Spring Boot or Go.

Aufgaben

• Design and build Agentic AI solutions with LLMs, tool calling and workflows.
• Build MCP servers and secure AI tools exposing MCN APIs and diagnostics.
• Develop production services using Python and Java/Spring Boot or Go.
• Build RAG/knowledge solutions using embeddings and vector databases.
• Deploy AI services on Docker/Kubernetes with CI/CD.
• Implement AI security and governance, including prompt-injection protection.
• Work with cross-functional teams to deliver production-ready AI capabilities.

Kenntnisse

Python development

Java/Spring Boot

Go

LLM/GenAI applications

Agentic AI systems

Tool calling & workflows

Kafka

Docker

Kubernetes

CI/CD

AI governance & security

Cloud platforms (AWS/Azure/GCP/OCI)

Tools

FastAPI

Pydantic

pytest

LangGraph

kagent

CrewAI

AutoGen

Langfuse

LangSmith

Ragas

OpenTelemetry

Docker

Kubernetes

Jobbeschreibung

Senior AI Engineer - Agentic AI Multi-Cloud Networking

Location: Bengaluru, India | Hybrid

Experience: 5-8 years | Full-time

Product: IZO+ Multi-Cloud Network (MCN)

About the Role

We are looking for a Senior AI Engineer with an AI-first engineering mindset to build production-grade Agentic AI capabilities for IZO+ MCN, our multi-cloud networking platform across AWS, Azure, GCP and OCI.

You will combine AI/LLM engineering, backend development and cloud-native technologies to build intelligent capabilities for network troubleshooting, operational insights, automation and governed remediation.

This is not a prompt-engineering role. You will take AI capabilities from concept agent tools/MCP MCN APIs production.

What You'll Do

• Design and build Agentic AI solutions using LLMs, tool/function calling, planning, workflows, memory and human-in-the-loop controls.
• Build MCP servers and secure AI tools exposing MCN APIs, cloud inventory, network diagnostics and product knowledge.
• Develop production services using Python and Java/Spring Boot or Go, integrating REST APIs, Kafka and event-driven workflows.
• Build RAG/knowledge solutions using embeddings, vector databases and retrieval optimization.
• Deploy and operate AI services on Docker/Kubernetes with CI/CD.
• Build AI evaluation and observability capabilities covering accuracy, tool-call correctness, latency, reliability and cost.
• Implement AI security and governance, including prompt-injection protection, validation, least-privilege access, auditability and approval controls.
• Use AI throughout the engineering lifecycle for design, development, testing, debugging and productivity.
• Work with Product, Architecture, Engineering, QA, SRE and Security teams to deliver production-ready AI capabilities.

Must Have

• 5-8 years of professional software engineering experience.
• Strong Python development skills; FastAPI, async programming, Pydantic and pytest.
• Strong production experience in Java/Spring Boot or Go.
• Hands‑on experience building LLM/GenAI applications using OpenAI, Anthropic, Gemini, AWS Bedrock, Azure AI Foundry, Vertex AI or equivalent.
• Proven experience building Agentic AI systems beyond simple prompt/response applications, including tool calling, multi-step workflows, state/memory and error handling.
• Hands‑on experience with MCP and at least one agent framework such as LangGraph, kagent, CrewAI, AutoGen or equivalent.
• Hands‑on experience with RAG, embeddings, vector databases and retrieval optimization.
• Experience with AI evaluation and observability, using technologies such as Langfuse, LangSmith, Ragas, DeepEval and/or OpenTelemetry.
• Strong understanding of AI security and responsible AI, including prompt‑injection protection, guardrails, validation, least‑privilege access and human approval mechanisms.
• Experience with Kafka and event‑driven architectures.
• Experience with Docker, Kubernetes and CI/CD.
• Production experience with at least one major public cloud – AWS, Azure, GCP or OCI.
• Strong software engineering fundamentals covering architecture, APIs, testing, debugging and production ownership.
• Demonstrated use of AI-assisted engineering for development, testing, debugging, documentation or productivity.

Good to Have

• Experience with multiple cloud platforms: AWS, Azure, GCP and OCI.
• Cloud networking: VPC/VNet, routing, DNS, NAT, BGP, IPsec, WireGuard.
• AWS Transit Gateway, Azure Virtual WAN, GCP Network Connectivity Center or OCI DRG.
• Dapr, Crossplane, Argo Events or Envoy.
• AIOps/NetOps, anomaly detection or automated remediation.
• Experience with Langfuse/LangSmith/Ragas/DeepEval/OpenTelemetry beyond the core AI evaluation requirement.
• Open-source contributions or cloud/AI certifications.

What Makes This Role Different

You will not just build AI applications. You will help build an AI-native multi-cloud networking platform where AI understands network context, reasons over operational data, interacts with enterprise tools and performs secure, governed actions in production.