Texas Capital is built to help businesses and their leaders. Our depth of knowledge and expertise allows us to bring the best of the big firms at a scale that works for our clients, with highly experienced bankers who truly invest in people’s success — today and tomorrow.
While we are rooted in core financial products, we are differentiated by our approach. Our bankers are seasoned financial experts who possess deep experience across a multitude of industries. Equally important, they bring commitment — investing the time and resources to understand our clients’ immediate needs, identify market opportunities and meet long-term objectives. At Texas Capital, we do more than build business success. We build long-lasting relationships.
Texas Capital provides a variety of benefits to colleagues, including health insurance coverage, wellness program, fertility and family building aids, life and disability insurance, retirement savings plans with a generous 401K match, paid leave programs, paid holidays, and paid time off (PTO).
Headquartered in Dallas with offices in Austin, Fort Worth, Houston, Richardson, Plano and San Antonio, Texas Capital was recently named Best Regional Bank in 2024 by Bankrate and was named to The Dallas Morning News’ Dallas-Fort Worth metroplex Top Workplaces 2023 and GoBankingRate’s 2023 list of Best Regional Banks. For more information about joining our team, please visit us at www.texascapitalbank.com.
Position Title
Engineer - Generative AI & Agentic AI (Mid-Level / Senior Associate)
Overview
We are seeking an experienced Engineer with 3-5 years of software engineering experience and demonstrated expertise in Generative AI and Agentic AI systems. This role bridges technical execution and architectural leadership, focusing on designing and delivering complex, scalable AI-powered solutions. The successful candidate will lead feature development, mentor junior engineers, and drive technical decisions that shape our AI platform strategy.
Key Responsibilities
Agentic AI Architecture & Design
Design end-to-end agentic AI systems including multi-agent architectures, orchestration frameworks, and agent lifecycle management
Implement advanced agent patterns (ReAct, Chain-of-Thought, hierarchical agents, swarm intelligence)
Build robust tool-calling frameworks and function composition systems
Design agent memory systems (short-term, long-term, episodic) with appropriate persistence strategies
Architect workflow engines for complex, multi-step autonomous processes
Lead design reviews and technical decisions for agentic AI components
Gen AI Systems & Optimization
Architect RAG pipelines including data ingestion, chunking strategies, embedding selection, and retrieval optimization
Implement advanced prompt engineering techniques (few-shot learning, chain-of-thought, structured outputs)
Optimize LLM performance through model selection, fine-tuning, and quantization strategies
Design and implement caching, batching, and inference optimization for cost and latency
Evaluate and integrate multiple LLM providers and models
Implement evaluation frameworks for measuring Gen AI system quality and safety
Production Systems & Scalability
Design scalable backend systems supporting high-throughput AI workloads
Implement robust error handling, retry logic, and graceful degradation for AI systems
Build monitoring, observability, and alerting for AI application health
Design database schemas and query patterns optimized for AI workloads
Lead capacity planning and performance optimization initiatives
Implement comprehensive logging and telemetry for debugging AI behavior
Code Quality & Architecture
Establish and enforce coding standards for AI systems
Design clean, maintainable architectures with clear separation of concerns
Lead architectural discussions and contribute to platform strategy
Mentor junior engineers through code reviews and technical guidance
Implement comprehensive testing strategies (unit, integration, end-to-end, adversarial)
Drive refactoring and technical debt reduction initiatives
Safety, Governance & Responsible AI
Implement guardrails and safety mechanisms for agent behavior
Design systems for monitoring and mitigating AI hallucinations and bias
Implement audit trails and explainability features for agent decisions
Ensure compliance with responsible AI principles and organizational policies
Lead threat modeling and security assessments for AI systems
Contribute to governance frameworks and AI ethics guidelines
Cross-Functional Leadership
Lead technical requirements gathering with product and business stakeholders
Translate complex business problems into agentic AI solutions
Collaborate with data science teams on model selection and evaluation
Lead technical relationships with AI platform vendors and providers
Present technical solutions and trade-offs to leadership
Participate in hiring and technical interviewing
Required Qualifications
Experience: 3-5 years of software engineering experience with shipped production systems
Gen AI/Agentic AI: 1+ year of hands-on experience building production Gen AI or Agentic AI applications
Programming: Expert-level proficiency in Python, TypeScript, or similar languages
System Design: Demonstrated ability to design scalable, maintainable systems; familiarity with system design concepts
Software Architecture: Strong understanding of design patterns, architectural principles, and trade-offs
Data Structures & Algorithms: Solid foundation in CS fundamentals
Database Design: Experience designing and optimizing relational and NoSQL databases
API Design: Experience designing and building production APIs
Testing & Quality: Ability to write comprehensive tests and ensure code quality
Strongly Preferred Qualifications
Gen AI & Agentic AI Expertise
Experience building production agentic systems (2+ shipped agents)
Hands-on work with multiple LLM providers (OpenAI, Anthropic, Google, open-source models)
Deep familiarity with agentic frameworks (LangChain, LlamaIndex, CrewAI, AutoGen, or similar)
Experience with advanced RAG patterns (hybrid search, reranking, query decomposition)
Knowledge of agent evaluation frameworks and benchmarking methodologies
Experience with prompt engineering at scale and fine-tuning LLMs
Understanding of agent safety, alignment, and ethical considerations
Infrastructure & DevOps
Experience with containerization (Docker) and orchestration (Kubernetes)
Proficiency with cloud platforms (AWS, Azure, GCP) and their AI services
MLOps experience: model versioning, experiment tracking, deployment pipelines
Experience with CI/CD systems and automated testing
Familiarity with observability tools (logging, metrics, tracing, distributed tracing)
Data & ML
Understanding of ML lifecycle and model evaluation techniques
Experience with embedding models and vector databases (Pinecone, Weaviate, Milvus)
Familiarity with feature engineering and data pipelines
Basic knowledge of prompt injection attacks and security considerations
Experience with A/B testing and experimentation frameworks
Domain Knowledge
Experience in customer-facing AI applications (chatbots, content generation, code assistants)
Background in process automation or workflow systems
Knowledge of specific domains (finance, healthcare, legal tech) where AI is applied
Experience with compliance-heavy or regulated environments
Key Technical Skills
Expert-Level:
Python or TypeScript
System design and architecture
Database design and optimization
RESTful API design and development
Software testing and quality assurance
Git and version control workflows
Production debugging and troubleshooting
Advanced Level:
LLM APIs and frameworks
Agentic AI design patterns
Vector databases and semantic search
Docker and containerization
Cloud platform services
SQL and database optimization
Asynchronous and concurrent programming
Intermediate+ Level:
ML concepts and model evaluation
Infrastructure and DevOps practices
Observability and monitoring
Security and threat modeling
Performance profiling and optimization
Soft Skills
Technical Leadership: Influences decisions, mentors others, sets technical direction
Communication: Explains complex technical concepts to diverse audiences; clear documentation
Problem-Solving: Approaches complex challenges systematically; balances pragmatism with perfection
Ownership: Takes end-to-end responsibility; proactive in identifying and solving problems
Collaboration: Works effectively across teams; builds consensus on technical decisions
Learning Agility: Rapidly masters new frameworks and keeps current with fast-evolving Gen AI landscape
Judgment: Makes sound technical trade-offs; knows when to optimize vs. when to move forward
User Empathy: Understands customer needs; advocates for user experience in technical decisions
Typical Week Activities
Designing and implementing features for agentic AI systems
Conducting architectural reviews for new initiatives
Mentoring junior engineers through code reviews and technical discussions
Evaluating new LLMs, frameworks, or tools for organizational adoption
Collaborating with product and data science on complex feature requirements
Optimizing system performance and addressing technical debt
Writing technical design documents and RFCs
Presenting technical solutions to leadership and stakeholders
Participating in on-call rotation for production systems
The duties listed above are the essential functions, or fundamental duties within the job classification. The essential functions of individual positions within the classification may differ. Texas Capital Bank may assign reasonably related additional duties to individual employees consistent with standard departmental policy.Texas Capital is an Equal Opportunity Employer.