2 months ago
Hyderābād, IndiaSenior
Responsibilities
- Write and optimize PySpark jobs on EMR on EKS and Delta Lake for large-scale data transformation.
- Design and build LLM-powered agents with tool calling, multi-step workflows, RAG, embeddings, vector search, grounding, guardrails, confidence gating, and human-in-the-loop review.
- Define agent tools and APIs and connect agents to internal systems and data sources, including through Model Context Protocol.
- Build and maintain Python services, shared libraries, and Kafka producers and consumers.
- Create prompt and agent evaluation harnesses and measure quality, cost, latency, and reliability in CI.
- Serve and monitor agents through APIs using LLM and agent observability.
- Write design documentation and collaborate with engineers and data scientists on architecture decisions.
- Use AI coding assistants while maintaining correctness and code quality.
Requirements
- Production experience with Python 3 and a web framework such as FastAPI, Flask, or Django.
- Hands-on experience with Spark or PySpark, EMR, EMR on EKS, Delta Lake, SQL, and large-scale data processing.
- Hands-on experience building LLM or agent-based features, including tool or function calling, multi-step workflows, RAG, and grounding output in real data.
- Experience with an LLM or agent framework or platform such as Amazon Bedrock, LangChain, LangGraph, LlamaIndex, OpenAI SDKs, or Anthropic SDKs.
- Experience with prompt engineering and evaluating LLM or agent output for quality and reliability.
- Experience handling sensitive data and PII with appropriate data-governance and privacy considerations.
- Experience with MongoDB, DocumentDB, PostgreSQL, or a similar database.
- Experience with AWS services such as S3 and EMR.
- Experience writing tests with pytest or a similar tool and working with Git.
- Comfort with Docker and Linux.
- Practical experience using AI coding assistants or agents such as Kiro, Cursor, GitHub Copilot, or Claude Code.
- Strong communication skills, including design documentation and cross-team collaboration.
- Preferred experience with Model Context Protocol, agent guardrails, evaluation pipelines, cost and latency tuning, caching, observability, lifecycle management, and quality regression detection.
- Preferred solid ML fundamentals and familiarity with precision, recall, F1, scikit-learn, pandas, and NumPy.
- Preferred experience with Delta Lake, AWS Glue, Athena, Kafka streaming, Kubernetes, EKS, Helm, GitOps, and Node.js, Python, or Java microservice environments.
- Preferred awareness of bias and explainability in AI systems.
Tech Stack
Apache KafkaApache SparkAWSDjangoDockerFastAPIFlaskGitHelmJavaKubernetesLinuxMongoDBNode.jsNumPyPandasPostgreSQLpytestPythonscikit-learnSQL
Categories
AI ApplicationsData Engineering
About Infor
Infor is a global leader in business cloud software products for companies in industry specific markets. Infor builds complete industry suites in the cloud and efficiently deploys technology that puts the user experience first, leverages data science, and integrates easily into existing systems. Over 60,000 organizations worldwide rely on Infor to help overcome market disruptions and achieve business-wide digital transformation. Here are some key insights: • 60,000+ customers • 100+ offices • 1,700+ support experts • 2,000+ partners • 17,000+ employees • 175+ countries where customers are located • 15,000+ cloud customers • 40+ countries with Infor offices