Full-Time
Lead Generative AI Engineer
Updated on 9/12/2026
Citi
10,001+ employees
Global financial services including banking, investment
No salary listed
Pune, Maharashtra, India
Hybrid
Bachelor's, Master's
 Software Engineering (1) |
|---|
Get referred to Citi
See people who can refer or advise you
- Deep hands-on expertise in core generative artificial intelligence concepts, including foundation models, large language models, embeddings, tokenization, and context-window management.
- Advanced prompt engineering and context engineering skills, including prompt design tools or frameworks and dynamic context orchestration.
- Strong experience building retrieval-augmented generation systems, including chunking strategies, hybrid search, and multi-vector retrieval.
- Practical experience designing knowledge graphs and Graph RAG pipelines using graph databases such as Neo4j or ArangoDB for relationship-aware, multi-hop retrieval.
- Proven experience building agentic artificial intelligence systems with Google Agent Development Kit or comparable frameworks such as LangGraph, Microsoft Agent Framework, CrewAI, or OpenAI Agents SDK, including tool or function calling, planning, and memory.
- Strong understanding of multi-agent orchestration patterns and harness engineering, including governance, feedback loops, execution controls, and agent isolation or sandboxing.
- Hands-on experience with agent interoperability protocols, including Model Context Protocol for tool and data access and Agent2Agent protocol for inter-agent collaboration.
- Experience with agent observability and evaluation, including tracing and OpenTelemetry-based tooling, for production agent systems.
- Proficiency with major generative artificial intelligence application programming interfaces such as OpenAI, Gemini, and Claude, and orchestration frameworks such as LangChain and LlamaIndex.
- Strong skills in natural language processing, including named entity recognition, dependency parsing, text classification, and topic modeling.
- Proficiency with vector databases and embedding models for large-scale retrieval.
- Experience with Docker, Kubernetes, and continuous integration and continuous delivery pipelines for artificial intelligence and agentic applications.
- Solid understanding of artificial intelligence compliance, guardrails, and responsible artificial intelligence practices.
- Strong Python skills and experience with data preprocessing, document ingestion, and application programming interface development.
- A bachelor's or master's degree in Computer Science, Data Science, AI, or a related field.
- Five to seven years of experience in artificial intelligence or software development, including significant experience in generative artificial intelligence and agentic artificial intelligence.
- A demonstrated portfolio of successful artificial-intelligence-driven projects in a business environment.
- Experience working with AWS or equivalent cloud infrastructure for artificial intelligence and generative artificial intelligence.
- Ability to collaborate with cross-functional teams.
- An analytical and proactive approach to problem-solving.
- Clear communication skills for technical and non-technical audiences.
- Collaborate with AI architects, leads, and stakeholders to design and implement generative and agentic AI solutions that address business challenges.
- Architect context engineering strategies, including context layering, chaining, compression, pruning or offloading, and memory management, to maximize reliability, provenance, and token efficiency in production.
- Design and implement advanced generative AI methods, including prompt engineering and retrieval-augmented generation.
- Build and optimize retrieval-augmented generation systems, including hybrid search, multi-vector retrieval, and re-ranking pipelines.
- Design and implement knowledge graphs and Graph RAG architectures for multi-hop reasoning, explainability, and traceable, grounded responses.
- Architect agentic workflows and multi-agent systems using Google Agent Development Kit and comparable frameworks, applying supervisor-worker, hierarchical, and peer-to-peer orchestration patterns.
- Design agent harnesses covering governance, constraints, feedback loops, state and session management, and execution controls for reliable and safe long-running agent systems.
- Integrate agents with tools and data through Model Context Protocol and orchestrate inter-agent collaboration and task delegation through Agent2Agent protocol.
- Support integration of generative AI and agentic applications into production environments, ensuring robust deployment, scalability, observability, and maintainability.
- Contribute to the development and optimization of real-time and streaming AI solutions.
- Stay current with advances in generative and agentic AI and share knowledge with the team.
- Ensure adherence to ethical AI guidelines, guardrails, agent isolation or sandboxing, data privacy, and compliance standards.
- Mentor junior team members, provide code reviews, and foster technical excellence.
Citi provides financial services including consumer banking, credit, investment banking, and wealth management to individuals, corporations, and governments. The company operates by earning interest on loans and collecting fees for managing investments, processing trades, and facilitating cross-border transactions through its digital platforms. Unlike many local banks, Citi maintains a physical and digital presence in over 160 countries, allowing it to serve as a single partner for clients with global financial needs. Its goal is to drive growth and profitability for its clients and shareholders while supporting environmental and social sustainability initiatives.
Company Size
10,001+
Company Stage
IPO
Headquarters
New York City, New York
Founded
1812
Get referred to Citi
See people who can refer or advise you
Simplify's Take
What believers are saying
- Q2 2026 revenue rose 14% to $24.8 billion, showing broad business momentum.
- Assets under custody and administration reached $35 trillion, up 22% year over year.
- Citi won $250 million from FundPark, expanding trade-finance and SME financing capacity.
What critics are saying
- Britain fined Citi £4.7 million on September 2, 2026 for Russia sanctions failures.
- Citi cut about 1,000 jobs in January 2026 and plans more March layoffs.
- China brokerage approval in September 2026 still leaves Citi exposed to CSRC rejection and delays.
What makes Citi unique
- Citi's Services franchise hit $6.4 billion in Q2 2026, led by TTS and Securities Services.
- Citi processed live tokenized-dollar transfers with DBS and SWIFT in minutes.
- Citi is launching Custody+ and Japan blockchain payments, extending global transaction-banking reach.
Help us improve and share your feedback! Did you find this helpful?
Benefits
Health Insurance
Dental Insurance
Vision Insurance
Life Insurance
Disability Insurance
401(k) Retirement Plan
401(k) Company Match
Wellness Program
Paid Vacation
Paid Sick Leave
Paid Holidays
Company News
Citigroup will launch instant cross-border payment services for Japanese companies using blockchain-based tokenized deposits as early as this year. The US bank claims this will be the first such service offered to Japanese clients by a foreign financial institution. The blockchain-based system will enable companies to make foreign-currency transfers instantly, including during nights and holidays when traditional banking systems are unavailable. The service represents an expansion of Citi's blockchain payment capabilities into the Japanese market, offering businesses greater flexibility in managing international transactions outside standard banking hours.
NEOM has secured approximately $3 billion in export credit agency financing from Italy's SACE under a long-term multicurrency untied facility. The deal, NEOM's first corporate ECA financing and the largest untied financing ever guaranteed by SACE, is backed by nine international banks including HSBC, Bank of America, and J.P. Morgan. The financing will support various projects across NEOM, particularly in infrastructure, urban development, construction, and transport. It will enable NEOM to leverage supplies from Italian businesses, especially SMEs. Italian suppliers and contractors have already supported NEOM projects with contracts worth $6.3 billion. The partnership aims to generate capital investment aligned with Saudi Vision 2030 and diversify the Kingdom's economy through foreign investment.
DBS and Citi completed a live cross-border US dollar payment on a Saturday in minutes using tokenized deposits through SWIFT's blockchain-based Digital Ledger. The transaction between DBS in Singapore and Citi's New York office took place on 5 September, whilst conventional transfers can take up to two business days. SWIFT declared its blockchain ledger ready for initial use in July, with 17 banks across six continents preparing live pilots. Participants include Citi, DBS, HSBC, Standard Chartered, UBS, BNY, Wells Fargo, BNP Paribas, and MUFG. Banks issue tokenised representations of deposits on their own ledgers, whilst SWIFT's shared ledger coordinates payment commitments. Final settlement occurs through existing infrastructure. Citi has already processed live transactions with First Abu Dhabi Bank and OCBC.
Citigroup is expected to receive Chinese regulatory approval for its fully owned mainland brokerage as early as this month, Reuters reported. The US bank applied for the licence in late 2021 as part of efforts to deepen its China operations. The bank plans to expand the unit's workforce to around 100 employees by year-end, roughly double current levels, according to sources. Recruitment will cover senior revenue-generating roles and operational positions through relocations and external hiring. The brokerage will seek permission for A-share trading, underwriting, research and principal trading. It aims to leverage Citi's existing mainland corporate relationships for equity and M&A work, focusing on technology, healthcare, consumer and financial sectors. Citi declined to comment on the application.
Anthropic, the developer behind Claude AI chatbot, has secured a $15 billion credit facility ahead of its initial public offering. Major financial institutions including Morgan Stanley, Goldman Sachs, JPMorgan Chase, and Citigroup are backing the arrangement. The facility significantly exceeds last year's $2.5 billion loan and surpasses the company's roughly $10 billion target. Anthropic now expects over $65 billion in annualised revenue, representing more than a sevenfold increase from its pace at the end of last year. Additional banks including Barclays and Bank of America have joined the arrangement. The timing coincides with renewed activity in the US IPO market, positioning Anthropic for a substantial market debut.