AI Engineer
Job Description
Hybrid role in Dallas, TX supporting production-grade AI and intelligent automation delivery. This position focuses on designing, building, integrating, and maintaining AI/ML and generative AI solutions with an emphasis on quality, scalability, and measurable user impact. You will work with modern LLM tooling and engineering workflows to improve delivery speed, code quality, and overall engineering efficiency.
Compensation: $50.00 - $52.00 per hour
Schedule: 40.0 hours per week
Location: Hybrid remote in Dallas, TX 75244
Experience: 2+ years
Education: Bachelor’s degree preferred
What you’ll do
- Develop, test, deploy, and support production-grade AI/ML, generative AI, and intelligent automation solutions.
- Address complex technical problems across development, integration, and production support through coding, debugging, testing, troubleshooting, and structured design remediation.
- Translate user requirements into technical designs, including APIs, workflows, and implementation patterns that are supportable over time.
- Build and integrate LLM, RAG, and agentic solution components into enterprise solutions, applications, and platforms.
- Support project delivery by executing disciplined work: estimation, documentation, status communication, and risk identification.
- Participate in design reviews and provide thoughtful trade-off analysis and implementation input.
- Use modern AI-assisted software engineering tools such as Claude Code, Codex, or equivalent agentic coding platforms as part of daily engineering delivery.
What you bring
- Experience designing, building, and maintaining production-grade LLM applications, including end-to-end pipelines from data ingestion through model output delivery (examples include Azure OpenAI, AWS Bedrock, Google Vertex AI).
- Practical experience building retrieval-augmented systems that ground model outputs in enterprise knowledge sources, including chunking strategies, embedding pipelines, and retrieval optimization (examples include LlamaIndex, LangChain, Pinecone, Weaviate, Azure AI Search, pgvector).
- Working technical knowledge of embedding models, vector search, and semantic retrieval patterns used to ground LLM outputs (examples include OpenAI Embeddings, Azure AI Search, pgvector).
- Prompt engineering proficiency, including zero-shot, few-shot, chain-of-thought, and structured output design, with the ability to evaluate and iterate on prompt performance (examples include DSPy, PromptFlow).
- Experience designing and building agentic systems, including multi-agent orchestration, tool use, and memory design across single and multi-step workflows (examples include LangGraph, AutoGen, CrewAI, Semantic Kernel, NVIDIA NIM).
- Ability to debug, troubleshoot, and remediate production LLM and agentic system failures across retrieval, orchestration, and generation layers.
- Hands-on software engineering proficiency in Python, delivering clean, modular, production-quality code for LLM pipelines and agentic applications.
- Experience working with structured and unstructured datasets, including data curation, preparation, and quality validation for model inputs and responses.
- Working familiarity with RESTful and event-driven API patterns, including asynchronous workflows, service boundaries, and integration of enterprise data sources to expose LLM and agentic capabilities.
- Practical understanding of containerization and orchestration concepts for cloud deployment (examples include Docker, Kubernetes, Azure Container Apps, AWS ECS).
- Understanding of AI/ML best practices, including modular code design, testing patterns for AI pipelines, and data quality validation.
- Familiarity with data monitoring and data observability in cloud environments (examples include OpenTelemetry, Azure Application Insights).
- Exposure to CI/CD and operationalization practices for AI systems, including model/workflow deployment, versioning, environment promotion, and release support in cloud or containerized environments.
- Clear communication skills to explain complex AI system behavior and trade-offs to technical and non-technical stakeholders, including risk and compliance.
- Strong ownership and accountability across the lifecycle from design through production and issue resolution.
- Ability to operate effectively as requirements, regulations, and technologies evolve; collaboration across engineering and product teams.
- Exposure to model observability and monitoring pipelines, including tracing multi-step agentic reasoning chains and detecting output degradation or behavioral drift (examples include LangSmith, Arize, Datadog, Azure Monitor).
- Familiarity with LLM fine-tuning approaches (examples include LoRA, QLoRA, PEFT, NeMo Framework) and responsible AI principles (bias and fairness evaluation, human-in-the-loop, explainability), especially in financial services contexts.
- Familiarity with cloud platforms for scalable LLM solutions (examples include Azure ML, AWS SageMaker, Google Vertex AI).
- Familiarity with AI-assisted software engineering tools that support development and code review (examples include Claude Code, GitHub Copilot, Codex).
- Strong grounding in AI/ML and deep learning fundamentals, with the ability to apply these concepts to shape enterprise AI solutions.
- 2+ years of applied engineering experience, including meaningful experience in AI/ML engineering roles.
Tools and technologies you may use
Python, Claude Code, Codex, Azure OpenAI, AWS Bedrock, Google Vertex AI, LlamaIndex, LangChain, Pinecone, Weaviate, Azure AI Search, pgvector, OpenAI Embeddings, DSPy, PromptFlow, LangGraph, AutoGen, CrewAI, Semantic Kernel, NVIDIA NIM, RESTful APIs, event-driven API patterns, asynchronous workflows, Docker, Kubernetes, Azure Container Apps, AWS ECS, OpenTelemetry, Azure Application Insights, CI/CD, LangSmith, Arize, Datadog, Azure Monitor, LoRA, QLoRA, PEFT, NeMo Framework, Azure ML, AWS SageMaker, GitHub Copilot, human-in-the-loop, embedding pipelines.