Job Description: Agentic AI Engineer
Experience: (8-10) + Years
Location: Fort Mill, SC
Job Summary
We are seeking an experienced Agentic AI Engineer with 10+ years of experience in software engineering, AI/ML, and enterprise application development to design, develop, and deploy intelligent AI agents for wealth management applications.
The ideal candidate will have strong expertise in Python, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), multi-agent architectures, and enterprise AI integration. This role requires hands-on experience building production-grade AI solutions that can reason, plan, use tools, retrieve information, and execute business workflows with appropriate human oversight.
Experience in wealth management, financial services, investment management, portfolio analytics, or financial advisory platforms is highly preferred.
Key Responsibilities
- Design, develop, and deploy production-ready Agentic AI solutions for wealth management and financial services applications.
- Build autonomous and semi-autonomous AI agents capable of planning tasks, reasoning, invoking tools, and executing multi-step workflows.
- Develop multi-agent systems using frameworks such as LangGraph, LangChain, Semantic Kernel, AutoGen, or equivalent technologies.
- Design and implement LLM-powered applications using models from OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, or similar platforms.
- Develop and optimize RAG pipelines, including document ingestion, chunking, embeddings, semantic search, reranking, and context retrieval.
- Integrate AI agents with enterprise systems, REST APIs, databases, knowledge repositories, and financial data platforms.
- Implement tool/function calling, structured outputs, workflow orchestration, memory management, and stateful agent execution.
- Build solutions for wealth management use cases, including portfolio research, advisor assistance, investment document analysis, client servicing, financial insights, and knowledge retrieval.
- Implement responsible AI practices, including guardrails, prompt-injection protection, access controls, PII protection, auditability, and human-in-the-loop approvals.
- Evaluate AI solutions for accuracy, groundedness, latency, reliability, cost, and business effectiveness.
- Deploy, monitor, and maintain AI applications using CI/CD, containerization, cloud services, logging, and observability tools.
- Collaborate with product managers, architects, data engineers, business analysts, and compliance teams to translate business requirements into scalable AI solutions.
- Mentor engineers, establish engineering best practices, and provide technical leadership across AI initiatives.
Required Technical Skills
1. Programming and Software Engineering
- Strong hands-on experience with Python and object-oriented programming.
- Expertise in REST APIs, microservices, asynchronous processing, and enterprise application integration.
- Proficiency with Git, automated testing, debugging, and software engineering best practices.
2. Agentic AI and LLMs
- Hands-on experience designing and implementing AI agents and multi-agent workflows.
- Strong understanding of LLM architecture, prompt engineering, context management, and model selection.
- Experience with agent orchestration frameworks such as LangGraph, LangChain, Semantic Kernel, or AutoGen.
- Experience implementing tool calling, function calling, planning, state management, retries, and error handling.
- Understanding of agent autonomy, workflow determinism, and human-in-the-loop controls.
3. RAG and Knowledge Retrieval
- Experience building enterprise-grade RAG applications and document intelligence solutions.
- Knowledge of embedding models, vector search, hybrid search, reranking, and retrieval optimization.
- Experience with vector databases such as Pinecone, Weaviate, Milvus, Chroma, or FAISS.
- Familiarity with Elasticsearch/OpenSearch and traditional relational or NoSQL databases.
4. Cloud and AI Deployment
- Experience deploying AI applications on AWS, Azure, or Google Cloud Platform.
- Familiarity with services such as AWS Bedrock, Azure OpenAI, or equivalent managed AI platforms.
- Experience with Docker, Kubernetes, CI/CD pipelines, and production monitoring.
- Understanding of scalability, performance optimization, model serving, and LLM cost management.
5. AI Quality, Security, and Governance
- Experience implementing LLM evaluation, hallucination mitigation, grounded responses, and AI guardrails.
- Knowledge of responsible AI, data privacy, secure API integration, and enterprise access controls.
- Understanding of observability, tracing, prompt/version management, and production incident troubleshooting.
Wealth Management Domain Experience
- Experience working in wealth management, financial services, investment management, banking, or fintech.
- Understanding of portfolio management, asset allocation, investment research, financial advisors, and client servicing workflows.
- Familiarity with financial statements, investment reports, market data, and financial research documents.
- Ability to develop AI solutions that support advisors and operations teams while maintaining data confidentiality, traceability, and compliance requirements.
- Experience with regulated financial environments and human approval workflows for sensitive or consequential actions is a strong plus.
Preferred Qualifications
- Bachelor's or Master's degree in Computer Science, Engineering, Artificial Intelligence, or a related field.
- 10+ years of overall software engineering experience, with substantial hands-on experience in AI/ML, LLM applications, or Generative AI.
- Demonstrated experience delivering AI solutions from proof of concept through production deployment.
- Strong analytical, problem-solving, communication, and stakeholder-management skills.
- Experience leading technical design discussions and mentoring engineering teams.
Important: Candidates should demonstrate hands-on implementation of production-grade Agentic AI solutions, not just chatbot development, prompt engineering, or proof-of-concept projects.
