NBBL- AI Engineer

National Payments Corporation of India (NPCI); Chennai, Mumbai Suburban; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

NPCI is seeking an AI Engineer to lead the design and delivery of autonomous AI agents and LLM-powered solutions for complex payment workflows in production. The role emphasizes building scalable agent architectures, tool use, memory, and multi-agent coordination across internal tools and APIs.

You will work with cross-functional teams to identify high-value use cases, implement RAG pipelines, and ensure low latency, secure, and cost-effective deployments on cloud platforms.

Qualifications

• Strong Python programming skills and asynchronous design patterns.
• Hands-on experience building LLM-powered applications with LangChain, LangGraph or similar frameworks.
• Solid understanding of agent design patterns (ReAct, planning, tool use, multi-agent collaboration).
• Experience deploying production systems on cloud platforms with Docker and CI/CD.
• Familiarity with MCP (Model Context Protocol) and system-level integration.

Responsibilities

• Design and develop single- and multi-agent systems with modern frameworks.
• Build agent capabilities: tool use, planning, memory, reflection, human-in-the-loop workflows.
• Integrate agents with external systems via APIs and MCP servers.
• Implement RAG pipelines using vector databases for context-aware behavior.
• Optimize prompts, agent loops and orchestration for accuracy and cost.
• Build evaluation harnesses and observability for agent performance.
• Collaborate with product, data, and engineering teams to ship production features.
• Stay updated on advances in LLMs and agent architectures.

Skills

Python programming

Async patterns

LangChain / LangGraph

LLM-powered apps

API integration

RAG pipelines

Docker / CI/CD

Cloud platforms (AWS/Azure/GCP)

NLP / ML basics

Education

BE/B.Tech / ME/M.Tech / MCA / MSc in AI/ML/DS or related fields

Tools

LangChain

LangGraph

LlamaIndex

CrewAI

AutoGen

Pinecone

LangSmith / Langfuse

APIs for LLMs (OpenAI, Anthropic, Gemini)

Job description

The opportunity

Lead AI projects and drive growth of the NBBL products by building and managing strategic AI agents and solutions. Own AI delivery, expand possibilities, and enable co-creation of innovative payment solutions while ensuring seamless execution through cross-functional collaboration. Design, build, and deploy autonomous AI agents that can reason, plan, use tools, and execute multi-step workflows. Will work at the frontier of LLM-based systems, building production-grade agents that integrate with internal tools, APIs, and enterprise data to automate complex business processes. .

Job details

Job Title: AI Engineer

Years of Experience: 7 yrs+

Education: BE/B.Tech / ME/M.Tech / MCA / MSc or equivalent (AI/ML/Data Science/Computer Science or related fields preferred)

Full-time

Location: Mumbai/ Hyderabad/Chennai

Permanent Role

Key responsibilities

1. Design and develop single- and multi-agent systems using frameworks like LangGraph, LangChain, CrewAI, AutoGen, or similar.

2. Build agent capabilities including tool use, planning, memory, reflection, and human-in-the-loop workflows.

3. Integrate agents with external systems via APIs, MCP (Model Context Protocol) servers, and custom connectors.

4. Implement RAG pipelines using vector databases (Pinecone, Weaviate, Qdrant, Chroma, etc.) for context-aware agent behavior.

5. Optimize prompts, agent loops, and orchestration for accuracy, latency, and cost.

6. Build evaluation harnesses, guardrails, and observability for agent performance (LangSmith, Langfuse, Arize, or similar).

7. Collaborate with product, data, and engineering teams to identify high-value agentic use cases and ship them to production.

8. Stay current with advances in LLMs, reasoning techniques, and agent architectures.

Key skills and experience required

1. Strong Python programming skills, including async patterns.

2. Hands-on experience building LLM-powered applications with frameworks such as LangChain, LangGraph, LlamaIndex, CrewAI, or AutoGen.

3. Solid understanding of agent design patterns: ReAct, planning, tool use, multi-agent collaboration, and memory.

4. Experience with leading LLM APIs (Anthropic Claude, OpenAI, Google Gemini, open-source models).

5. Working knowledge of RAG, embeddings, and vector databases.

6. Prompt engineering and structured output techniques (function calling, JSON schemas, tool definitions).

Experience deploying production systems on AWS / Azure / GCP, with Docker and CI/CD.

8. Experience with MCP (Model Context Protocol), browser-use, or computer-use agents.

9. Fine-tuning, LoRA, or model distillation experience.

10. Knowledge of evaluation frameworks (RAGAS, DeepEval, custom evals).

11. Experience with workflow orchestration (Temporal, Airflow, Prefect). 12. Familiarity with safety, alignment, and red-teaming practices for LLM systems.

13. Background in NLP, ML, or applied research.