Mastercard
Pune, Maharashtra, India Posted 2d ago
You will design, build, and ship production-grade agentic AI systems for the Operational Intelligence Program within Business and Market Insights at Mastercard.
Key Responsibilities
Architect and build the tool-calling layer that powers agents by wrapping internal services, data platforms, and external APIs.
Engineer reliable tool execution at scale, including parallel and chained tool calls, retries, and error recovery.
Develop high-performance Python backend services for LLM orchestration, caching, and distributed workflows.
Engineer state, memory, and context management subsystems to maintain session continuity.
Architect multi-agent and skills-based agent systems using frameworks such as LangGraph, CrewAI, or AutoGen.
Build observability for agent behavior, including end-to-end tracing of tool calls.
Build retrieval systems using vector databases and knowledge graphs.
Establish LLMOps and MLOps pipelines on Databricks covering MLflow and prompt evaluation.
Design multimodal generative AI pipelines that unify text, image, tabular, and graph data.
Guide fine-tuning, prompt engineering, and alignment strategies to adapt foundation models.
Requirements
Bachelor's or Master's degree in Computer Science, AI/ML, or Engineering
Strong track record of building and operating production backend systems at scale
Strong API design and integration experience
Excellent Python engineering skills including async programming and microservices
Hands-on experience shipping at least one LLM-powered application to production
