22 hours ago
Mumbai, India or Bengaluru, IndiaStaff+
Responsibilities
- Architect and lead complex multi-agent AI workflows for advanced reasoning, planning, tool use, memory, and autonomous execution.
- Translate risk-domain business problems into technical requirements and develop robust end-to-end AI solutions.
- Build and optimize agentic workflows, retrieval pipelines, memory layers, tool-use sequences, and RAG systems.
- Develop scalable Python microservices and FastAPI APIs to expose AI capabilities.
- Implement document ingestion, embeddings, and vector search using services such as Azure AI Search and Pinecone.
- Containerize and deploy AI services with Docker and Kubernetes while contributing to reliable release pipelines.
- Implement observability, tracing, debugging, evaluation harnesses, and model-quality validation for AI workflows.
- Apply AI risk, safety, governance, machine learning, deep learning, and natural language processing expertise to enterprise solutions.
Requirements
- 6+ years of professional experience in a role combining software development and data science or machine learning.
- Expert-level Python skills and a track record of designing scalable backend services and APIs, preferably with FastAPI.
- Hands-on experience designing and building solutions with multiple agentic frameworks, including LangChain, LangGraph, CrewAI, AutoGen, or Semantic Kernel.
- Extensive experience architecting and optimizing RAG systems and integrating vector databases such as OpenSearch, Pinecone, or Weaviate.
- Experience designing and deploying Docker/Kubernetes AI systems on AWS, Azure, or GCP.
- Strong experience with MLOps principles, observability, evaluation frameworks, and release processes for LLM-based systems.
- In-depth understanding of AI risk, safety, and enterprise governance requirements.
- Strong background in machine learning, deep learning, natural language processing, and Transformer architectures.
- Preferred: experience leading LLM evaluation harnesses, deep Langfuse or comparable observability experience, and hands-on AWS Bedrock, Azure AI Foundry, or GCP Vertex AI expertise.
- Preferred: knowledge of GraphRAG and advanced multi-hop retrieval strategies; AWS certifications or equivalent; and experience in financial services or another highly regulated industry.
Benefits
- Full-time position.
- Equal opportunity employer with reasonable accommodation support for applicants with disabilities.
Tech Stack
Categories
About Citi
Citi is a public financial-services company offering consumer and institutional banking, credit cards, wealth management, treasury and trade solutions, and capital-markets services. It serves individuals, corporations, financial institutions, and governments in more than 160 countries and jurisdictions, earning interest and fee income from lending, payments, trading, and advisory. Founded in 1812 and headquartered in New York, it trades on the NYSE under the ticker C.