Senior Python Generative AI Engineer

Job Title: Senior Python Generative AI Engineer Overview: We are seeking an experienced Python Generative AI Engineer to design, build, and productionize LLM-driven applications that improve business workflows, customer experience, and decision-making. In this role, you will lead the end-to-end delivery of GenAI solutions—covering model selection, RAG architectures, evaluation, MLOps, and secure deployment—while mentoring engineers and partnering with product, data, and security teams. Location & Work Mode: Irving, TX (Hybrid). You will work onsite 2–3 days per week with flexibility for remote work on remaining days. Key Responsibilities: Lead the design and implementation of Generative AI solutions using Python, including chatbots, summarization, knowledge assistants, and automation copilots. Build Retrieval-Augmented Generation (RAG) pipelines: document ingestion, chunking strategies, embeddings, vector search, reranking, and citation/grounding. Integrate LLM providers and frameworks (OpenAI/Azure OpenAI, Anthropic, or open-source models) using LangChain/LlamaIndex and custom orchestration where needed. Develop robust evaluation harnesses for LLM outputs (accuracy, faithfulness, toxicity, latency, cost), including offline test sets and human-in-the-loop review workflows. Operationalize models and services with MLOps practices: CI/CD, model/version tracking, prompt management, observability, and rollback strategies. Implement API services (FastAPI/Flask) and asynchronous processing for high-throughput workloads; optimize performance and cost via caching, batching, and token controls. Ensure security and compliance: PII redaction, data governance, access controls, secrets management, audit logging, and safe prompt/response handling. Mentor team members, conduct code reviews, define best practices, and collaborate with stakeholders to translate requirements into scalable technical solutions. Required Skills & Experience: 8+ years of software engineering experience with strong Python proficiency (typing, packaging, testing, performance profiling). Hands-on experience building GenAI applications with LLMs, prompt engineering, function/tool calling, and structured outputs (JSON schemas). Strong knowledge of RAG systems, vector databases (Pinecone, Weaviate, Milvus, or FAISS) and embedding models. Experience with one or more LLM orchestration frameworks: LangChain, LlamaIndex, Semantic Kernel (Python). API and microservices development using FastAPI/Flask; integration with enterprise systems and event-driven patterns. MLOps/DevOps experience: Docker, Kubernetes, CI/CD (GitHub Actions/Azure DevOps), monitoring/logging (Prometheus/Grafana/ELK). Data skills: SQL, data modeling, ETL/ELT concepts; familiarity with data lakes/warehouses (Snowflake/Databricks is a plus). Cloud experience in Azure/AWS/GCP (Azure preferred for enterprise GenAI deployments). Education & Certifications: Bachelor’s degree in Computer Science, Software Engineering, Data Science, or related field (Master’s preferred). Preferred certifications: AWS Certified Machine Learning – Specialty, Microsoft Azure AI Engineer Associate, Databricks certifications, or Kubernetes (CKA/CKAD).