Python Gen AI Developer

Job Title and Overview We are seeking a Python GenAI Developer with ~6 years of experience to design and build generative AI solutions that accelerate business workflows, enable intelligent search, and improve customer and employee experiences. In this role, you will develop LLM-powered applications, integrate them into production systems, and collaborate with product, data, and platform teams to deliver secure, scalable AI capabilities. Location & Work Mode Irving, TX — Hybrid work model (typically 2–3 days onsite per week, subject to team needs). You will work closely with local engineering and data stakeholders and partner with distributed teams. Key Responsibilities Design and implement LLM-powered services (RAG, function/tool calling, summarization, extraction, classification) using Python and modern GenAI frameworks. Build retrieval pipelines using vector databases (e.g., Pinecone/Weaviate/FAISS) and search platforms (e.g., OpenSearch/Elasticsearch) with optimized chunking, embeddings, and reranking strategies. Develop robust prompt engineering patterns, evaluation harnesses, and guardrails (PII redaction, content filtering, policy enforcement) to improve quality and reduce risk. Integrate GenAI services with enterprise systems via REST/gRPC APIs; implement authentication/authorization, rate limiting, and observability. Operationalize models and pipelines: containerize services (Docker), deploy to cloud (AWS/Azure/GCP), and implement CI/CD, monitoring, and incident response runbooks. Implement automated evaluation and testing (unit/integration, prompt regression, offline/online metrics) and iterate based on user feedback and telemetry. Collaborate with data engineering on data access, document ingestion, metadata management, and governance; ensure compliance and auditability. Provide technical leadership through design reviews, mentoring, and establishing best practices for GenAI architecture, code quality, and MLOps standards. Required Skills & Experience 6+ years of software development experience with strong proficiency in Python (FastAPI/Flask preferred). Hands-on experience building GenAI applications with LangChain and/or LlamaIndex ; familiarity with OpenAI/Anthropic/Azure OpenAI or similar APIs. Experience with RAG architectures , embeddings, vector search, and relevance optimization (chunking, reranking, hybrid search). Strong knowledge of APIs (REST), microservices patterns, and backend engineering fundamentals. Working experience with SQL and at least one database (PostgreSQL/MySQL) plus NoSQL (MongoDB/DynamoDB) is a plus. Cloud and DevOps exposure: Docker , CI/CD (GitHub Actions/Jenkins/Azure DevOps), and observability (logging/metrics/tracing). Security and compliance mindset: secrets management, IAM, data privacy/PII handling, and secure SDLC. Agile delivery experience (Scrum/Kanban), strong communication, and cross-functional collaboration. Education & Certifications Bachelor’s degree in Computer Science , Software Engineering , Data Science , or a related field required; Master’s degree is a plus. Preferred certifications include AWS Certified Developer , AWS/Azure Solutions Architect , or Microsoft Azure AI Engineer Associate (or equivalent). Additional Information You’ll join a collaborative engineering culture that values experimentation, measurable outcomes, and clean, maintainable systems. We offer competitive benefits (medical/dental/vision, 401(k), paid time off), learning budgets for GenAI/cloud training, and opportunities to grow into staff-level engineering, architecture, or AI platform leadership tracks. Salary Range Estimated annual base salary for Irving, TX: $130,000 – $165,000 USD (depending on experience, interview performance, and domain expertise), plus potential bonus and benefits.