23 hours ago
Pune, IndiaMid Level
Responsibilities
- Construct multi-step AI agents and orchestration workflows using agentic design patterns.
- Build production features with foundation models and deploy enterprise AI and agentic gateways for routing, caching, load balancing, rate limiting, and cost tracking.
- Develop secure integration layers connecting AI models with enterprise databases, codebases, and APIs through the Model Context Protocol.
- Build semantic search, document ingestion, RAG, vector retrieval, and memory-management pipelines.
- Deploy, version, monitor, and operate AI services using containerization, cloud infrastructure, model-serving architectures, and MLOps hubs.
- Manage infrastructure costs, compute scaling, hardware selection, endpoint security, access controls, and data privacy compliance.
- Build automated evaluation platforms and CI/CD testing harnesses for prompts, RAG outputs, and multi-agent systems.
- Collaborate with product managers, engineering managers, SREs, Infosec, and frontend and backend engineers to deliver end-to-end experiences.
Requirements
- Bachelor’s or master’s degree in Computer Science, Software Engineering, Artificial Intelligence, or a related field.
- At least four years of software development experience, including at least two years building, testing, and shipping agentic workflows, memory systems, and LLM features to production.
- Proven experience deploying stateful AI systems, complex tool-calling agents, or enterprise API gateway integrations.
- Hands-on experience with multi-agent design patterns, state machines, LangGraph, and stateful memory management tools.
- Practical experience configuring AI gateways for routing, fallbacks, and cost tracking.
- Experience building evaluation harnesses with tools such as DeepEval and Ragas.
- High proficiency in Python and/or TypeScript; Rust or Java understanding is preferred.
- Experience with vector stores such as Pinecone, pgvector, Milvus, or Qdrant and with embedding models.
- Experience with RESTful or GraphQL APIs, Docker, Kubernetes, and enterprise cloud infrastructure such as AWS, GCP, or Azure.
Tech Stack
Categories
About PUMA
PUMA designs, manufactures, and sells athletic and sportstyle footwear, apparel, and accessories for athletes and lifestyle consumers worldwide. The public company (ETR: PUM), founded in 1948 and headquartered in Herzogenaurach, Germany, goes to market through wholesale, retail, and direct-to-consumer e-commerce, and owns the Cobra Golf and stichd brands. Its product lines span football, running, training, and everyday wear across more than 100 countries.