Role : GenAI Engineer
Location : Irving, TX (Hybrid)
Project Mission: To lead the design, development, and delivery of the highly complex backend system that forms the core intelligence of the analytics platform. This role is responsible for architecting a scalable, performant, and resilient service that translates natural language into actionable data insights, while mentoring a team of engineers to achieve technical excellence.
Key Responsibilities:
a. Technical Leadership & Architecture: Lead the architectural design and development of all backend services. Make critical decisions regarding microservice boundaries, API design, data processing logic, and the overall orchestration flow.
b. GenAI Orchestration: Architect and oversee the implementation of the core orchestration agent. This includes designing the Retrieval-Augmented Generation (RAG) strategy, defining sophisticated prompt engineering templates, and ensuring robust, fault-tolerant integration with LLM APIs.
c. Team Mentorship and Guidance: Mentor and guide a team of backend engineers (both local and remote). Decompose complex features into actionable tasks, conduct thorough code reviews to ensure quality and adherence to best practices, and foster a culture of technical ownership and collaboration.
d. Code Quality and Best Practices: Set and enforce standards for backend development, including coding style, testing strategies (unit, integration), documentation, and security.
e. System Performance and Scalability: Profile and optimize the performance of the entire backend system, from vector database query latency to LLM API response times, ensuring the platform can scale to meet user demand.
f. Cross-Functional Collaboration: Act as the primary technical point of contact for the backend. Partner closely with the Solutions Architect to align with the overall vision, and collaborate with the Lead Frontend Engineer and Lead Data Engineer to define clear API contracts and data handoffs.
Required Skills & Experience:
g. Extensive experience as a Senior or Lead Backend Engineer, with a proven track record of delivering complex, data-intensive applications.
h. Expert-level proficiency in a primary backend language, Python.
i. Demonstrated ability to architect and design distributed systems and microservices-based architectures.
j. Deep, hands-on experience developing applications with Generative AI frameworks (e.g., LangChain, LangGraph, LlamaIndex) and a strong command of the underlying concepts (RAG, prompt engineering, embeddings).
k. Proven experience leading a software development team, including mentoring junior engineers and managing technical tasks.
l. In-depth knowledge of REST API design, Vector Databases (e.g., Pinecone, PGvector), and SQL/NoSQL databases.
m. Excellent problem-solving skills and the ability to navigate technical ambiguity in a rapidly evolving domain like GenAI.
n. Expertise in containerization (Docker) and orchestration platforms (Kubernetes, OpenShift, GKE).
Never miss an opportunity! Create an alert based on the job you applied for.
