3 days ago
Pune, IndiaStaff+
Responsibilities
- Design and implement generative AI and agentic AI solutions for enterprise business challenges.
- Architect context engineering strategies including layering, chaining, compression, pruning, offloading, and memory management.
- Build and optimize RAG systems with hybrid search, multi-vector retrieval, chunking, and re-ranking pipelines.
- Design knowledge graphs and Graph RAG architectures for multi-hop reasoning, explainability, and grounded responses.
- Architect agentic workflows and multi-agent systems using Google ADK and comparable frameworks.
- Develop agent harnesses with governance, constraints, feedback loops, state and session management, execution controls, and agent isolation.
- Integrate agents with tools and data through MCP and enable inter-agent collaboration through A2A.
- Support production deployment, scalability, observability, maintainability, and real-time or streaming AI solutions.
- Apply ethical AI, guardrails, sandboxing, data privacy, and compliance practices.
- Mentor junior team members, review code, and share technical knowledge.
Requirements
- Bachelor's or master's degree in Computer Science, Data Science, AI, or a related field.
- 5–7 years of experience in AI or software development, including significant generative AI and agentic AI experience.
- Hands-on expertise with foundation models, LLMs, embeddings, tokenization, and context-window management.
- Advanced prompt and context engineering experience, including dynamic context orchestration.
- Experience building RAG systems, knowledge graphs, Graph RAG pipelines, and large-scale retrieval systems.
- Experience with Google ADK or comparable agent frameworks such as LangGraph, Microsoft Agent Framework, CrewAI, or OpenAI Agents SDK.
- Knowledge of multi-agent orchestration, tool and function calling, planning, memory, harness engineering, and agent interoperability protocols.
- Experience with agent observability and evaluation, including tracing and OpenTelemetry-based tooling.
- Proficiency with major generative AI APIs and orchestration frameworks such as OpenAI, Gemini, Claude, LangChain, and LlamaIndex.
- Strong NLP skills, including named entity recognition, dependency parsing, text classification, and topic modeling.
- Experience with Docker, Kubernetes, CI/CD pipelines, AWS or equivalent cloud infrastructure, data preprocessing, document ingestion, and API development.
- Understanding of AI compliance, guardrails, and responsible AI practices.
- Demonstrated portfolio of successful AI-driven projects in a business environment.
- Strong collaboration, communication, analytical, proactive problem-solving, learning, and mentoring skills.
Tech Stack
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.