Software Developer (Emerging Careers)

We’re a leader in data and AI. Through our software and services, we inspire customers around the world to transform data into intelligence - and questions into answers.

If you're looking for a dynamic, fulfilling career with flexibility and a world-class employee experience, you'll find it here. We're recognized around the world for our inclusive, meaningful culture and innovative technologies by organizations like Fast Company, Forbes, Newsweek and more.

The Platform Products division is looking for a Software Developer (Emerging Careers) specialized in Generative AI to join the engineering team driving SAS Retrieval Agent Manager. In this role, you will help build and scale cutting-edge, enterprise-grade Retrieval-Augmented Generation (RAG) and autonomous agent architectures. 

You will play a pivotal role in integrating SAS VIYA agentic technologies with vectorized customer document data, ensuring our LLM-driven solutions are secure, high-performing, and highly scalable. This is an opportunity to directly shape how enterprise customers deploy GenAI at scale by engineering the production-grade infrastructure and guardrails that let sophisticated agentic systems run reliably and respond accurately in mission critical environments. 

• Collaborate on the ingestion, processing, and management of vectorized customer document data to optimize retrieval accuracy, latency, and agentic integrations. 
• Maintain accountability for the entire lifecycle of the code, from translation of product requirements into actionable features, to rigorous testing (functional, unit, and performance), code reviews, and post-deployment support. 
• Design, develop, and maintain autonomous agent architectures and RAG pipelines using LangChain to interface seamlessly with SAS VIYA offerings. 
• Integrate rigorous LLM defensive frameworks and operational Guardrails to ensure safe, compliant, and deterministic model behaviors across enterprise data. 
• Build and execute systematic validation frameworks to quantify LLM performance, tracking key metrics (such as context recall, faithfulness, and answer relevance) to ensure the highest output quality. 
• Embrace curiosity, passion, authenticity and accountability. These are our values and influence everything we do.

• Bachelor's degree in Computer Science, Artificial Intelligence, Data Science, or a related technical field 
• Minimum 2 years of experience in software development 
• Production-level Python development experience with a deep understanding of object-oriented design patterns, memory optimization, and asynchronous programming. 
• Hands-on experience building complex, stateful applications using LangChain or similar orchestrators. 
• Hands-on experience developing and integrating Model Context Protocol (MCP) servers and clients to expose tools, data sources, and APIs for consumption by LLM-driven agents in production environments. 
• Experience deploying LLM-as-a-judge or empirical evaluation tooling (e.g., Ragas, TruLens, MLflow) to bench and score generative outputs. 
• Practical experience creating, deploying, and managing containerized cloud workloads using Docker or Kubernetes. 
• Proficiency with version control (git, GitHub workflows, branching strategies, and rigorous code reviews).  
• Equivalent combination of related education, training and experience may be considered in place of the above qualifications.

• Adaptability: Approaches architectural shifts and evolving GenAI trends with a growth mindset, treating rapid technological changes as opportunities for innovation.
• Collaborating: Actively seeks input from cross-functional teams, leveraging collective engineering strengths to solve complex data and orchestration challenges.
• Communication: Translates complex AI concepts and metric evaluation data into clear, actionable technical insights for both technical stakeholders and product management. 
• Quality Orientation: Demonstrates a vigilant commitment to minimizing hallucination, optimization bottlenecks, and security vulnerabilities in production GenAI deployments. 
• Experience working directly with vector databases, embeddings, and complex document parsing methodologies.
• Experience with cloud computing platforms such as Azure, AWS, or Google Cloud, and ideally their AI services e.g. Azure Open AI.
• Experience implementing safety, alignment, or content-filtering layers (e.g., NeMo Guardrails, Guardrails AI) within LLM pipelines.
• Experience with CI/CD deployment automation tools like GitHub Actions or Jenkins.
• Exposure to project management frameworks and tracking tools like Jira for task tracking, sprint planning and collaboration. 

At SAS, it’s not about fitting into our culture – it’s about adding to it. We believe our people make the difference. Our inclusive workforce brings together unique talents and inspires teams to create amazing software that reflects the diversity of our users and customers.

To qualify, applicants must be legally authorized to work in the United States, and should not require, now or in the future, sponsorship for employment visa status. SAS is an equal opportunity employer. All qualified applicants are considered for employment without regard to any characteristic protected by law. Read more: Know Your Rights. 

Resumes may be considered in the order they are received. SAS employees performing certain job functions may require access to technology or software subject to export or import regulations. To comply with these regulations, SAS may obtain nationality or citizenship information from applicants for employment. SAS collects this information solely for trade law compliance purposes and does not use it to discriminate unfairly in the hiring process.

SAS only sends emails from verified “sas.com” email addresses and never asks for sensitive, personal information or money. If you have any doubts about the authenticity of any type of communication from, or on behalf of SAS, please contact Recruitingsupport@sas.com.

Let's stay in touch! Join our Talent Community to stay up to date on company news, job updates and more.

#SAS