AI Engineer II
Mastercard21 hours ago
Pune, IndiaMid Level
Responsibilities
- Architect and build reliable tool-calling layers that integrate internal services, data platforms, and external APIs with clear schemas, contracts, and permissions.
- Engineer scalable tool execution with parallel and chained calls, timeouts, retries, idempotency, error recovery, and graceful handling of failures or poor model outputs.
- Develop high-performance Python backend services for LLM orchestration, including asynchronous processing, streaming, caching, rate limiting, and distributed workflows.
- Build agent state, memory, context management, multi-agent systems, skills-based agents, and production observability for agent behavior.
- Build RAG and Graph-RAG retrieval systems using vector databases and knowledge graphs.
- Establish LLMOps and MLOps pipelines covering evaluation, lineage tracking, CI/CD, and monitoring.
- Design multimodal generative AI pipelines and guide fine-tuning, prompt engineering, alignment, safety, explainability, and Responsible AI practices.
- Evaluate and productionize agentic AI, multimodal model, and foundation model advances against enterprise performance and safety requirements.
- Lead, mentor, and grow engineers while setting Gen AI engineering standards across the program.
Requirements
- Bachelor's or Master's degree in Computer Science, AI/ML, or Engineering, or equivalent practical experience.
- Strong track record building and operating production backend systems at scale, including distributed services, APIs, asynchronous processing, data stores, and observability.
- Strong API design and integration experience for safe and reliable service and LLM interactions.
- Excellent Python engineering skills, including asynchronous programming, API development, microservices, and SQL proficiency.
- Hands-on experience shipping at least one production LLM-powered application using tool or function calling, with OpenAI, Anthropic, Gemini, or open-source models.
- Working understanding of prompt design, embeddings, semantic search, and agent memory, or demonstrated ability to learn these domains quickly.
- Experience with at least one cloud platform; AWS is preferred, while Azure and GCP are also accepted.
- Experience leading or mentoring engineers, communicating effectively, managing stakeholders, and translating technical work into business value.
- Preferred experience includes Model Context Protocol, tool servers and connectors, agent-performance evaluation, fine-tuning, multimodal models, knowledge graphs, or MLOps tooling such as MLflow, Weights & Biases, SageMaker, or Bedrock.
Tech Stack
Categories
About Mastercard
Mastercard builds and operates a global payments network used by banks, merchants, fintechs, and governments, offering card processing, real-time payments, tokenization, and fraud/risk services. It generates revenue from transaction processing and assessment/service fees across more than 200 countries and territories. Founded in 1966 and headquartered in Purchase, New York, Mastercard is a public company listed on the NYSE (ticker: MA).