Senior Forward Deployed AI Engineer - Vice President
citigroupBrooklyn (NY)
Senior Forward Deployed AI Engineer - Vice President
Posted today
citigroupBrooklyn (NY)
SENIORITY
Senior
About the role
Overview:
In this role you build production-grade AI agent reasoning and integration pipelines to connect enterprise systems. You will develop MCP servers, robust error handling, and HITL escalation, working with cross-functional squads to ensure safety and quality. You’ll integrate guardrails and testbeds, shaping automated AI workflows for scalable, compliant deployments. This is a hands-on engineering role that combines backend development with AI tooling to deliver enterprise-ready AI capabilities. Compensation / Benefits medical, dental & vision coverage 401(k) life, accident, and disability insurance wellness programs paid time off (vacation, sick leave) paid holidays
Responsibilities:
Develop production-quality agent reasoning logic, memory management, and sub-agent delegation in Python Build custom Model Context Protocol (MCP) servers connecting AI agents to enterprise systems (ServiceNow, JIRA, DBaaS, Kafka, internal REST/gRPC services) Implement resilient error handling with retries, fallbacks, and HITL escalation triggers Integrate Lakera Guardrails for prompt-injection defense, jailbreak mitigation, and PII filtering/redaction Collaborate with C12 engineers to create automated regression testbeds and integrate Agentflow Studio evaluation harnesses into deployment workflows Mentor and coach junior developers, participate in sprint delivery and peer code reviews Assess risk in business decisions to safeguard Citi's reputation and ensure compliance with laws and regulations
Key requirements:
6+ years of software engineering experience 4+ years of professional Python proficiency Hands-on experience with LLM APIs (R2D2 Gateway, OpenAI, Google Vertex AI) REST/gRPC API development, Docker, Git, Linux, and CI/CD automation Understanding of prompt engineering, structured JSON output validation (Pydantic), and vector search/retrieval patterns Proven ability to work in fast-paced agile squads solving ambiguous technical problems Bachelor’s degree; Master’s preferred collaborative mindset ability to coach and mentor others strong problem-solving and communication Python LLM APIs (R2D2 Gateway, OpenAI, Vertex AI) REST/gRPC APIs
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.