Lead Specialty Software Engineer (Gen AI)

Wells Fargo & Company•Charlotte, NC

1d•Hybrid

About The Position

Wells Fargo is seeking a Lead Specialty Software Engineer (GenAI) to design, develop, and deliver enterprise‑grade Generative AI solutions that drive automation, improve operational efficiency, and support modernization. This role blends hands‑on engineering, GenAI system design, and technical leadership, leveraging the enterprise AI ecosystem—including Tachyon GenAI Studio, RAG frameworks, and approved LLM platforms. The Lead Engineer will partner across product, architecture, data, cyber, and risk teams to ensure high‑quality GenAI delivery aligned with Wells Fargo engineering standards and the Product Operating Model. In this role, you will: Lead complex initiatives, ensuring systems are monitored, efficient, and risk-mitigated while identifying opportunities to optimize processes and reduce cost. Design, architect, and implement end‑to-end GenAI solutions—including RAG pipelines, multi‑agent workflows, prompt frameworks, evaluation tooling, and safety controls—aligned with enterprise engineering, privacy, security, and governance standards. Build scalable APIs, backend services, retrieval systems, and vector‑storage patterns; select appropriate LLMs, embeddings, and retrieval strategies based on business needs and cost/performance constraints. Write production‑grade code (Python, Java, or Node) and lead development of advanced GenAI features such as tool‑calling, hybrid retrieval, workflow automation, and model‑evaluation pipelines. Provide architectural guidance, code reviews, hands‑on debugging, and mentorship to elevate engineering quality, velocity, and modern DevOps practices (CI/CD, test automation, telemetry). Leverage the Tachyon GenAI ecosystem—GenAI Studio, sandbox environments, prototyping APIs, and fine‑tuning—to build reusable components, standardize retrieval patterns, and support enterprise‑wide adoption. Ensure robust governance and security through content‑filtering, PII/PHI‑safe patterns, prompt‑hardening, adversarial testing, secure‑development practices, and complete documentation for risk, cyber, and audit reviews. Collaborate with product managers, architects, data engineers, cyber, risk, and operations teams to define use cases, estimate effort, plan work, and deliver multi-team GenAI initiatives within the Product Operating Model. Communicate technical decisions clearly to stakeholders and leaders, partner effectively with production support and platform engineering, and lead teams to meet objectives. Mentor less‑experienced engineers and contribute to overall engineering excellence across teams.

Requirements

5+ years of Specialty Software Engineering experience, or equivalent demonstrated through one or a combination of the following: work experience, training, military experience, education
3+ years with Microsoft Dynamics 365
1+ year of experience with GenAI experience

Nice To Haves

Experience with enterprise GenAI environments (e.g., Tachyon GenAI Studio).
Familiarity with multi‑agent orchestration, embeddings, retrieval optimization, and evaluation methods.
Understanding of enterprise security, AI governance, or model‑risk frameworks.
Experience coaching engineers or leading scrum teams.
5+ years of backend or full‑stack engineering; strong distributed‑systems experience.
2+ years working with LLMs, GenAI, agent frameworks, vector DBs, or RAG systems.
Hands‑on experience with Python and/or Java; familiarity with LangChain, LlamaIndex, HuggingFace, etc.
Experience deploying on AWS/Azure and containerized environments.
Strong knowledge of data engineering, APIs, microservices, and observability.

Responsibilities

Lead complex initiatives, ensuring systems are monitored, efficient, and risk-mitigated while identifying opportunities to optimize processes and reduce cost.
Design, architect, and implement end‑to‑end GenAI solutions—including RAG pipelines, multi‑agent workflows, prompt frameworks, evaluation tooling, and safety controls—aligned with enterprise engineering, privacy, security, and governance standards.
Build scalable APIs, backend services, retrieval systems, and vector‑storage patterns; select appropriate LLMs, embeddings, and retrieval strategies based on business needs and cost/performance constraints.
Write production‑grade code (Python, Java, or Node) and lead development of advanced GenAI features such as tool‑calling, hybrid retrieval, workflow automation, and model‑evaluation pipelines.
Provide architectural guidance, code reviews, hands‑on debugging, and mentorship to elevate engineering quality, velocity, and modern DevOps practices (CI/CD, test automation, telemetry).
Leverage the Tachyon GenAI ecosystem—GenAI Studio, sandbox environments, prototyping APIs, and fine‑tuning—to build reusable components, standardize retrieval patterns, and support enterprise‑wide adoption.
Ensure robust governance and security through content‑filtering, PII/PHI‑safe patterns, prompt‑hardening, adversarial testing, secure‑development practices, and complete documentation for risk, cyber, and audit reviews.
Collaborate with product managers, architects, data engineers, cyber, risk, and operations teams to define use cases, estimate effort, plan work, and deliver multi-team GenAI initiatives within the Product Operating Model.
Communicate technical decisions clearly to stakeholders and leaders, partner effectively with production support and platform engineering, and lead teams to meet objectives.
Mentor less‑experienced engineers and contribute to overall engineering excellence across teams.