AI Engineer
Role details
Job location
Tech stack
Job description
- Build and maintain applications in .NET within an AWS environment.
- Develop proof-of-concepts for chatbot, agentic AI, and LLM use cases, iterating toward production-ready features.
- Create LLM-based objects and integrations using AWS Bedrock and its available tooling.
- Design and build tools and features that support chatbot functionality, including conversation flows and tool/function calling.
- Write production-quality code, including clean APIs, automated testing, and CI/CD pipelines.
- Collaborate with business stakeholders and engineering teams to define and deliver realistic GenAI solutions.
- Prototype experiments and harden them into reliable, deployed features.
- Help establish patterns for prompt engineering, orchestration, and evaluation as AI capabilities mature.
- Set up and maintain LLMOps workflows, including deployment, monitoring, and cost tracking.
- Work with security, privacy, and compliance teams to ensure solutions meet enterprise standards.
Requirements
An emerging technology team focused on developing and deploying AI-driven solutions is seeking an AI Engineer. We are looking for a versatile Software Engineer with AWS experience who can contribute across both traditional application development and emerging AI capabilities. The initial work will be centered on proof-of-concepts for chatbots and LLM-based features, alongside day-to-day development tasks., Education: A BA/BS degree in Computer Science, CIS, MIS, or a related field is required.
Experience: 5+ years in software engineering with experience building and shipping production applications. Experience or familiarity with LLMs, chatbot frameworks, and agentic AI patterns is needed.
Technical Skills: A strong development background in .NET or Python is required, along with hands-on AWS experience with Bedrock. Candidates must have skills in API design, secure integrations, automated testing, and CI/CD pipelines.
Preferred Qualifications
- Experience with or exposure to RAG pipelines, including embeddings and vector databases (FAISS, Pinecone, OpenSearch).
- Comfortable with Python alongside .NET for AI/ML-related work.