Software Engineer, Applied Artificial Intelligence (AI)

ABS is seeking an exceptional Software Engineer to join our Applied Artificial IntelIigence (AI) Practice Team. In this full-time role, you will design, build, and deploy intelligent systems that move beyond research into production at scale. You will focus on architecting and evaluating multi-agent systems, retrieval-augmented generation (RAG) pipelines, and fine-tuned large language models delivering AI capabilities that drive measurable business impact.

What You Will Do:

• Build at the frontier: Design and implement end-to-end AI systems, including multi-agent workflows, retrieval pipelines, and customized LLMs.
• Engineer full-stack solutions: Deliver web and backend applications that seamlessly integrate AI, ensuring reliability, scalability, and strong user experience.
• Raise the bar on evaluation: Develop rigorous truth sets, automated quality checks, and real-time monitoring pipelines to quantify performance and business outcomes.
• Prototype rapidly: Transform research concepts into production-grade systems through fast iteration, disciplined testing, and continuous refinement.
• Shape best practices: Contribute to internal standards for applied AI development, evaluation, and deployment at scale.

• Bachelor's degree in Computer Science, Engineering, or a related field.
• 5+ years of software development experience, including 3+ years building production-grade AI systems.
• Proven track record delivering AI agents, RAG pipelines, or fine-tuned models with measurable business impact.
• Experience designing evaluation frameworks and truth sets for applied AI quality assurance.

Knowledge, Skills, and Abilities

• Strong expertise in agent frameworks and LLM orchestration (API-first development, Vercel AI SDK, LangChain, etc.).
• Deep knowledge of RAG architectures, embeddings, vector databases, and retrieval optimization strategies.
• Experience with LLM fine-tuning, prompt design, and model performance evaluation.
• Full-stack engineering skills across modern web and backend technologies.
• Familiarity with MLOps practices: CI/CD, model versioning, monitoring, and deployment at scale.
• Strong grounding in applied information retrieval and vector-based systems.