Senior Forward Deployed AI Engineer - Vice President

The Applied AI and Agents Factory brings together ambitious engineers to turn advanced AI capabilities into production-ready solutions. Working directly with business and technology teams, you’ll tackle complex engineering challenges, build intelligent agents and take ideas from initial concept through to live deployment. This is an opportunity to work at the cutting edge of AI engineering, developing systems that go beyond conversational tools to reason, plan and execute multi-step workflows. You’ll take ownership of the full engineering lifecycle, from agent architecture and orchestration to enterprise integration, security and observability. With a strong focus on hands-on engineering, collaboration and rapid delivery, the Factory gives you the opportunity to solve challenging technical problems, influence architectural decisions and help shape reusable tools and engineering standards adopted across Citi. The Senior Forward Deployed Engineer is a hands-on core engineering professional embedded within Line of Business squads. This role is responsible for developing production-grade agent reasoning logic, custom tool integrations, data retrieval pipelines, and resilient execution workflows adhering to enterprise safety, security, and quality standards. Responsibilities:  Agent Reasoning & Logic Implementation: Write clean, modular, production-quality Python code implementing agent reasoning loops, dynamic tool calling, short-term/long-term memory management, and sub-agent delegation.  Tool & MCP Server Development: Build and maintain custom Model Context Protocol (MCP) servers and API connectors integrating AI agents with enterprise systems (e.g., ticketing systems, relational/NoSQL databases, message queues, and internal REST/gRPC microservices).  Data Ingestion & Retrieval Pipelines: Develop and optimize Retrieval-Augmented Generation (RAG) components, including document parsing, embedding generation, vector indexing, metadata filtering, and semantic search retrieval.  Resilience & Error Handling: Implement resilient error handling, automated retry mechanisms with exponential backoff, circuit breaking, fallback routines, and Human-in-the-Loop (HITL) escalation triggers for ambiguous model outputs.  Structured Output Validation: Build deterministic validation layers using Pydantic and JSON Schema to guarantee structured, type-safe outputs from non-deterministic foundation models.  Safety & Guardrail Integration: Integrate real-time AI guardrail policies for prompt injection defense, jailbreak mitigation, and automated PII filtering/redaction into agent execution loops.  Collaborative Testing & Evals: Partner with C12 engineers to construct automated regression testbeds, curate golden datasets, and integrate automated evaluation suites into CI/CD release pipelines.  Agile Sprint Delivery & Peer Review: Actively participate in agile sprint delivery, technical problem-solving sessions, and peer code reviews, coaching junior engineers on software craftsmanship.  Direct Business Collaboration: Collocates and collaborates directly with Line of Business end-users (traders, bankers, analysts) to observe day-to-day operational workflows and capture nuanced domain logic and edge cases.  Iterative Prototype Building: Rapidly builds, tests, and refines functional agent prototypes and prompt chains based on direct, daily qualitative feedback from business pilot users.  User Friction Analysis: Analyzes user interaction logs and user feedback to identify model failure modes, prompt ambiguities, and UI/UX friction, implementing iterative improvements to agent reasoning.  Appropriately assess risk when business decisions are made, demonstrating particular consideration for the firm's reputation and safeguarding Citi, its clients and assets, by driving compliance with applicable laws, rules and regulations, adhering to Policy, applying sound ethical judgment regarding personal behavior, conduct and business practices, and escalating, managing and reporting control issues with transparency.  Qualifications :  Total Experience: 6+ years of professional software engineering experience, with 4+ years of strong, professional Python, Java, or Go proficiency.  LLM & AI Engineering: 2+ years of hands-on experience working with foundation model APIs (e.g., centralized enterprise AI gateways, OpenAI, Azure OpenAI, Google Vertex AI, Anthropic) and integrating LLMs into backend services.  Software Engineering Fundamentals: Solid experience in REST/gRPC API development, Docker, Git workflows, Linux environments, and CI/CD pipelines.  Prompt & Data Engineering: Proven understanding of advanced prompt engineering techniques, structured output parsing, vector databases, and retrieval strategies.  Experience collaborating directly with business stakeholders, product managers, or operational users in rapid, iterative delivery cycles.  Education:  Bachelor’s/University degree or equivalent experience; Master’s degree preferred.  ------------------------------------------------------ Job Family Group: Technology ------------------------------------------------------ Job Family: Applications Development ------------------------------------------------------ Time Type: ------------------------------------------------------ Primary Location: New York New York United States ------------------------------------------------------ Primary Location Full Time Salary Range: $142,320.00 - $213,480.00 In addition to salary, Citi’s offerings may also include, for eligible employees, discretionary and formulaic incentive and retention awards. Citi offers competitive employee benefits, including: medical, dental & vision coverage; 401(k); life, accident, and disability insurance; and wellness programs. Citi also offers paid time off packages, including planned time off (vacation), unplanned time off (sick leave), and paid holidays. For additional information regarding Citi employee benefits,