AI Engineer II
Salary not listed • Pune, India • Full-time
Posted 5d ago
About the job
Mastercard's Business & Market Insights (B&MI) group is seeking a Senior AI Engineer specializing in Generative AI & ML Engineering for its Operational Intelligence Program. This role focuses on designing, building, and deploying production-grade agentic AI systems that leverage extensive tool calls into enterprise services and APIs. You will work on complex multi-step workflows, ensuring secure, scalable, and reliable results. The position involves deep engagement with agent orchestration, tool calling, memory management, retrieval, and LLMOps, aiming to set the engineering standard for Generative AI development and mentor other engineers. This is a hands-on role with a strong emphasis on backend engineering for individuals with significant experience in production services and LLM development.
Responsibilities
- Architect and build the tool-calling layer for agents, wrapping internal services, data platforms, and external APIs as tools with defined schemas and permissions.
- Engineer reliable tool execution at scale, handling parallel/chained calls, timeouts, retries, idempotency, error recovery, and failures.
- Develop high-performance Python backend services for LLM orchestration, including async job handling, streaming, caching, rate limiting, and distributed workflows.
- Engineer state, memory, and context management subsystems for agents to maintain session continuity in long, multi-step interactions.
- Architect multi-agent and skills-based agent systems using frameworks like LangGraph, CrewAI, or AutoGen for autonomous reasoning and coordination.
- Build observability for agent behavior, including end-to-end tracing, tool-selection accuracy measurement, and debugging.
- Build retrieval systems (RAG and Graph-RAG) using vector databases and knowledge graphs for grounded agent knowledge.
- Establish LLMOps and MLOps pipelines on Databricks (AWS) for MLflow, prompt/agent evaluation, lineage tracking, CI/CD, and monitoring.
- Design multimodal generative AI pipelines integrating text, image, tabular, and graph data using transformer and foundation models.
- Guide fine-tuning, prompt engineering, and alignment strategies (PEFT, LoRA, instruction tuning, RLHF) to adapt foundation models.
- Implement Responsible AI practices, including hallucination mitigation, bias detection, output safety, and data ethics compliance.
- Evaluate and productionize advances in agentic AI, multimodal models, and foundation models.
- Lead, mentor, and grow a team of engineers, setting the engineering standard for Gen AI development.
Requirements
- Bachelor's or Master's degree in Computer Science, AI/ML, or Engineering, or equivalent practical experience.
- Strong track record of building and operating production backend systems at scale (distributed services, APIs, async processing, data stores, observability).
- Strong API design and integration experience for building services callable by LLMs.
- Excellent Python engineering skills, including async programming, API development (FastAPI or similar), microservices, and SQL proficiency.
- Hands-on experience shipping at least one LLM-powered application to production using tool/function calling.
- Working understanding of Gen AI engineering patterns (prompt design, embeddings, semantic search, agent memory) or ability to ramp up quickly.
- Experience with at least one cloud platform (AWS preferred; Azure or GCP welcome).
- Experience leading or mentoring engineers, with strong communication and stakeholder management skills.
- Nice to have: experience with Model Context Protocol (MCP) or building tool servers/connectors for LLM agents.
- Nice to have: experience evaluating agent performance.
- Nice to have: exposure to fine-tuning, multimodal models, knowledge graphs, or MLOps tooling.