Senior Full Stack GenAI Engineer

Our client is seeking a Senior Full Stack GenAI Engineer to help design, build, and deploy next-generation AI-driven applications. This hands-on role combines software engineering, architecture, and applied AI expertise to create scalable, secure, and modern solutions leveraging GenAI tools, LLMs, and AWS services. The ideal candidate will have a strong full-stack foundation in Python and Java, extensive experience with microservices and CI/CD pipelines, and a passion for developing innovative AI-powered systems. This position offers the opportunity to shape the client's AI strategy and influence platform direction through experimentation, prototyping, and deployment of real-world GenAI applications. Key Responsibilities • Design and implement scalable GenAI architectures using large language models (LLMs), multimodal models, and retrieval-augmented generation (RAG). • Develop and deploy AI-powered applications leveraging Python/Java, microservices, and cloud-native design patterns. • Integrate AI and GenAI capabilities into enterprise applications using APIs, SDKs, and orchestration frameworks such as LangChain and Bedrock. • Build and maintain CI/CD pipelines for AI and full-stack applications, ensuring automation, versioning, and efficient deployment. • Fine-tune and optimize models using techniques such as instruction tuning, RLHF, quantization, and distillation. • Experiment with emerging GenAI tools and frameworks (e.g., Hugging Face, LlamaIndex, DeepEval, RAGAS). • Implement responsible AI practices, including bias detection, hallucination mitigation, and explainability. • Collaborate with cross-functional product and architecture teams to align technical decisions with business goals. • Stay ahead of industry trends and drive innovation within the GenAI and full-stack development ecosystem. Required Qualifications • 10+ years of total software engineering experience, including 5+ years full-stack development (Python/Java). • 3+ years working directly with GenAI frameworks and tools (e.g., LangChain, Hugging Face, Bedrock, vector databases). • Hands-on experience building and deploying GenAI applications in production environments. • Strong background in modern architecture styles - microservices, APIs, and event-driven systems. • Expertise with AWS services (SageMaker, Bedrock, Comprehend, Lex) or equivalent cloud platforms. • Experience with CI/CD pipelines, containerization (Docker, Kubernetes), and ML workflow tools (MLflow, DVC). • Strong understanding of LLMs, embeddings, and vector databases (e.g., FAISS, Pinecone, Weaviate). • Excellent communication and problem-solving skills with the ability to work collaboratively in cross-functional teams. Preferred Qualifications • AWS AI/ML certification. • Familiarity with AI testing frameworks such as DeepEval or RAGAS. • Financial services or large enterprise environment experience. • Knowledge of prompt engineering, few-shot learning, and agent-based systems. Role Details • Location: Hybrid (3 days onsite in Plano, TX - Tuesday through Thursday) • Contract: 6-12 months (possibility of extension or conversion) • Interview Process: • MS Teams - Technical Screening (30 min) • Onsite - 1 hour (includes coding)