Agentic AI Engineer

AI Engineer – Agentic AI & Production SystemsLocation: New York City, NY (Onsite/Hybrid)Employment Type: W2 ContractContract Length: Long-Term ContractStart Date: ASAPInterview Process: 3 StagesAbout the RoleWe are seeking an experienced AI Engineer to join a leading enterprise technology team building next-generation AI solutions at scale. This role focuses on designing, developing, and deploying production-grade agentic AI systems, intelligent workflows, and Retrieval-Augmented Generation (RAG) platforms that deliver measurable business value.You will work closely with engineering, product, and business stakeholders to build scalable, observable, and secure AI applications in a production environment.Key ResponsibilitiesDesign and implement production-ready agentic AI workflows and autonomous systems.Build and optimize Retrieval-Augmented Generation (RAG) pipelines, including hybrid search, semantic retrieval, re-ranking, and prompt optimization.Develop scalable APIs and backend services using Python and modern engineering practices.Design and implement multi-agent and single-agent architectures using industry-standard frameworks and patterns.Integrate AI solutions with enterprise applications, databases, APIs, and external tools.Implement observability, monitoring, logging, and alerting across AI systems.Develop evaluation frameworks, guardrails, and hallucination detection capabilities.Optimize prompt performance, token consumption, and context management.Build and maintain CI/CD pipelines supporting AI workloads and deployments.Collaborate with cross-functional teams to deliver production-quality solutions.Required Skills & ExperienceProven experience building and deploying AI applications or agentic workflows into production.Strong Python development experience.Hands-on experience with LangGraph and/or LangChain.Experience designing and implementing RAG architectures.Experience with vector databases such as Pinecone, Weaviate, pgvector, or similar technologies.Experience developing APIs using FastAPI or equivalent frameworks.Understanding of prompt engineering, context management, and LLM application development.Experience with CI/CD pipelines and modern software delivery practices.Strong software engineering fundamentals, including testing, monitoring, and documentation.Preferred SkillsModel Context Protocol (MCP) / FastMCPCrewAI, AutoGen, Semantic KernelOpenTelemetry, Grafana, TempoKafka, MongoDB, ElasticsearchDocker and KubernetesAWS, Azure, or GCPJava development experienceAI evaluation frameworks and LLM guardrailsExperience implementing feedback loops and AI performance monitoringNice to HaveFinancial Services or Banking experienceExperience working within regulated enterprise environmentsExposure to risk, compliance, or governance-focused AI solutionsInterview ProcessStage 1: Technical ScreeningStage 2: AI Engineering & System Design InterviewStage 3: Final Client / Stakeholder InterviewAdditional InformationLong-term W2 contract opportunity.New York City-based candidates preferred.Candidates outside New York must be willing to travel and work onsite as required.Offer will be contingent upon successful completion of background verification checks.Immediate availability or short notice preferred.