Senior AI Platform Engineer

Teradata; Bengaluru; On-site; INR 300,000 - 500,000; Full time

Job summary

Teradata Group is seeking an AI engineering professional in Bengaluru to architect and deploy production-grade AI agents and backend services. You will develop scalable microservices, implement MCP integrations, and ensure observability and reliability across LLM-powered workflows.

You will collaborate with AI researchers, engineers and data scientists to tackle multi-agent coordination, real-time monitoring, and drift detection in enterprise environments.

Qualifications

• Bachelor's or Master’s degree in Computer Science, Engineering or related field.
• 3+ years of backend programming experience (Python, Go).
• Hands-on experience building agents using LangGraph/LangChain/CrewAI and MCP servers.
• Direct experience with LLM frameworks and multi-agent orchestration systems.
• Direct experience with relational databases (PostgreSQL) and vector stores.

Responsibilities

• Develop and maintain backend microservices and APIs (REST, gRPC) to support Teradata AI Studio capabilities.
• Build, orchestrate, and deploy autonomous AI agents using LangGraph, LangChain, or CrewAI.
• Implement tool calling, dynamic routing, and MCP integrations for multi-agent workflows.
• Manage application lifecycles with observability and production incident resolution.
• Integrate and optimize stateful data layers including PostgreSQL and vector stores for agent memory and RAG pipelines.

Skills

Python

Go

LLM observability

Education

Bachelor's or Master's in CS/Engineering

Tools

LangGraph

LangChain

CrewAI

MCP (Model Context Protocol)

Job description

Our Company

At Teradata, we believe that people thrive when empowered with better information. Teradata Autonomous Knowledge Platform activates enterprise intelligence by unifying data, knowledge and business context to achieve tangible outcomes. With Teradata, organizations can provide agents with full context for impact when it matters. Our solution lets businesses connect and scale on premises, in the cloud, or through a hybrid approach. Teradata delivers real business value with AI.

What You’ll Do

At Teradata, we’re not just managing data; we’re unleashing its full potential. Our Teradata AI Studio platform and pioneering Enterprise Vector Store are empowering the world’s largest enterprises to derive unprecedented value from their most complex data. We’re rapidly pushing the boundaries of what’s possible with Artificial Intelligence, especially in the exciting realm of autonomous and agentic systems

We’re building intelligent systems that go far beyond automation — they observe, reason, adapt, and drive complex decision-making across large-scale enterprise environments. As a member of our AI engineering team, you’ll play a critical role in designing and deploying advanced AI agents that integrate deeply with business operations, turning data into insight, action, and measurable outcomes.

In this role, you’ll architect foundational components for production-grade AI systems — from agent frameworks and LLM pipelines to observability and evaluation layers that ensure reliability, accountability, and performance. You’ll be responsible not just for building models, but for making them measurable, debuggable, and trustworthy in real-world, high-stakes deployments.

You’ll work alongside a high-caliber team of AI researchers, engineers, and data scientists tackling some of the hardest problems in AI and enterprise software — from scalable multi-agent coordination and fine-tuned LLM applications, to real-time monitoring, drift detection, and closed-loop retraining systems.

If you’re passionate about building intelligent systems that are not only powerful but observable, resilient, and production-ready, this role offers the opportunity to shape the future of enterprise AI from the ground up.

Key Responsibilities:

• Develop and maintain robust backend microservices and APIs (REST, gRPC) to support Teradata AI Studio capabilities.
• Build, orchestrate, and deploy autonomous AI agents using frameworks like LangGraph, CrewAI, or AutoGen.
• Implement tool calling, dynamic routing, and Model Context Protocol (MCP) integrations for multi-agent workflows.
• Manage full application lifecycles, including application-level observability (e.g., OpenTelemetry, Langfuse) and production incident resolution.
• Integrate and optimize stateful data layers, including vector databases and relational databases (e.g., PostgreSQL) for agent memory and RAG pipelines.
• Implement AI-specific observability and tracing for LLM pipelines and multi-agent workflows to monitor performance, token usage, and response quality.

Who You’ll Work With

Imagine collaborating daily with some of the brightest minds in the company – individuals who champion diversity, equity, and inclusion as fundamental to our success. You’ll be part of a cohesive force, laser-focused on delivering high-quality, critical, and highly visible AI/ML functionality within the Teradata Cloud platform. Your insights will directly shape the future of our intelligent data solutions.

You’ll report directly to the inspiring Sr. Manager, Software Engineering, who will champion your growth and empower your contributions.

What Makes You A Qualified Candidate

• A Bachelor’s or Master’s degree in Computer Science, Engineering or a related field – your academic foundation is key.
• Core Programming: 3+ years of experience with any of the backend languages (Python, Go).
• Agent Frameworks: Hands-on experience building agents using frameworks like LangGraph, Langchain, CrewAI, etc. and integrating Model Context Protocol (MCP) servers.
• Direct experience building applications with LLM frameworks and multi-agent orchestration systems.
• Data Management: Direct experience managing relational databases (PostgreSQL) and Vector stores.
• API Design: 2+ years in building and managing REST or gRPC APIs and microservices for the application layer.

What You’ll Bring

• Hands-on experience with LLM observability, tracing, and evaluation platforms (e.g., Langfuse, LangSmith, Arize Phoenix, or OpenTelemetry for AI).
• Experience with LLM-specific tools and frameworks (LangChain, vector databases, prompt engineering).
• Experience with infrastructure security and compliance standards.
• Contributions to open-source projects or technical communities.
• Strong problem-solving skills and ability to work in a collaborative team environment.
• Ownership mindset with a focus on reliability, scalability, and continuous improvement.

#LI-VB1