6 days ago
Pune, IndiaStaff+
Responsibilities
- Design, develop, test, deploy, and operate production-grade Semantic Data Agents using Google ADK, LangChain, LangGraph, or equivalent frameworks.
- Build reusable semantic assets including certified metrics, KPIs, dimensions, hierarchies, business rules, policies, and contextual definitions.
- Implement source grounding, data lineage, confidence scoring, explainability, policy validation, auditability, and human-in-the-loop controls.
- Consume and expose governed tools through Model Context Protocol services for agent-to-agent communication and decision support.
- Lead the Semantic Layer Squad’s technical execution, sprint planning, stand-ups, backlog grooming, code reviews, and delivery.
- Mentor junior and mid-level developers and promote AI-assisted software development practices.
- Collaborate with Distribution, Data Services, AI design, and Enterprise Architecture teams on APIs, schemas, data contracts, and platform standards.
- Implement logging, tracing, metrics, observability, secure token handling, data masking, and enterprise security controls.
- Build automated evaluation and validation frameworks for grounding, hallucination prevention, confidence, reasoning transparency, lineage, and guardrails.
Requirements
- Minimum 8–10+ years of progressive software engineering experience with strong hands-on coding and production delivery experience.
- Minimum 2–3+ years of dedicated professional experience in AI engineering, prompt engineering, machine learning, generative AI, or agentic AI systems.
- Expert-level Python proficiency, including hands-on experience with FastAPI, PySpark, Flask, LangChain, LangGraph, Google ADK, or equivalent agentic frameworks.
- Experience implementing source grounding, fact verification, confidence scoring, provenance tracking, human-in-the-loop workflows, and AI evaluation using tools such as Ragas, TruLens, DeepEval, or Phoenix.
- Proven experience integrating, consuming, and exposing tools in an enterprise Model Context Protocol architecture.
- Deep familiarity with Oracle, SQL Server, MongoDB, advanced SQL, and secure REST/gRPC API and microservice design.
- Hands-on experience with Linux deployment pipelines, Harness or Jenkins, Docker, Kubernetes, Red Hat OpenShift, and Autosys.
- Experience using generative AI tools such as GitHub Copilot, Claude, or ChatGPT for coding, testing, and workflow optimization.
- Experience with Java and Spring Boot is strongly preferred.
- Experience with knowledge graphs, metadata registries, ontologies, domain-driven design, event-driven architecture, Apache Kafka, and enterprise architecture standards is preferred.
- Familiarity with Starburst, Trino, Presto, Splunk, Prometheus, and Grafana is preferred.
- Experience leading agile development teams, running sprints, and managing technical delivery using Jira and Confluence.
- Bachelor’s degree in computer science, information technology, artificial intelligence, or a related quantitative field.
Tech Stack
Apache KafkaDockerFastAPIFlaskGrafanagRPCHarnessJavaJenkinsKubernetesLinuxMicrosoft SQL ServerMongoDBOpenShiftPhoenixPrestoPrometheusPythonSplunkSpring BootSQL
Categories
About Citi
Citi's mission is to serve as a trusted partner to our clients by responsibly providing financial services that enable growth and economic progress. Our core activities are safeguarding assets, lending money, making payments and accessing the capital markets on behalf of our clients. We have over 200 years of experience helping our clients meet the world's toughest challenges and embrace its greatest opportunities. We are Citi, the global bank – an institution connecting millions of people across hundreds of countries and cities. For information on Citi’s commitment to privacy, visit on.citi/privacy.