Ekaiva Inc is hiring a Senior AI Engineer to design, build, and deploy machine learning and AI solutions that convert complex data into reliable, product-ready insights. The role is based in Chicago, IL (onsite) and centers on agentic AI, knowledge architecture (including GraphRAG), application engineering with .NET, and the observability and governance needed to operate AI agents at scale.
You’ll work across the full lifecycle of model and system development, from preparation and evaluation through deployment, while partnering with teams to deliver scalable solutions. This position also involves engineering secure agent execution environments and integrating AI capabilities into enterprise applications.
What you’ll do
- Design, build, and deploy machine learning and artificial intelligence solutions that turn complex data into useful insights and reliable products.
- Guide model development from data preparation and statistical analysis through evaluation and deployment, partnering with teams to deliver scalable systems.
- Develop and evaluate dependable AI models that help teams make better-informed decisions and deliver more useful data-driven services.
- Build multi-agent systems, autonomous workflows, and agentic operating platforms.
- Set up Model Context Protocol (MCP), define custom tools/plugins, and create sandbox environments for secure agent execution.
- Create and query combined Graph + Vector embeddings (GraphRAG) from heterogeneous document sources.
- Build clean semantic layers, knowledge bases, and grounding mechanisms for LLMs.
- Integrate AI capabilities into enterprise applications using C# / .NET.
- Perform advanced prompt optimization, chain-of-thought structuring, guardrailing, and context window management.
- Build centralized observability platforms to configure, provision, distribute, and monitor AI agents across multiple frameworks.
Required experience and skills
- Hands-on experience building multi-agent systems, autonomous workflows, and agentic operating platforms.
- Expertise in setting up MCP, defining custom tools/plugins, and creating sandbox environments for secure agent execution.
- Experience with AWS Bedrock, Anthropic Claude, Microsoft Copilot Studio, and GitHub Copilot extensions/CLIs.
- Demonstrated ability to create and query Graph + Vector embeddings (GraphRAG) from heterogeneous document sources.
- Deep understanding of DDL and DML operations within Vector Databases (e.g., Pinecone, Milvus, Qdrant, PGVector) and GraphQL APIs.
- Expertise in building clean semantic layers, knowledge bases, and grounding mechanisms for LLMs.
- Strong background in C# / .NET for integrating AI capabilities into enterprise applications.
- Advanced prompt optimization, chain-of-thought structuring, guardrailing, and context window management.
- Proven ability to build centralized observability platforms to configure, provision, distribute, and monitor AI agents across multiple frameworks.
- Experience tracking latency, token usage, cost, evaluation metrics (evals), and agent execution traces (e.g., LangSmith, Phoenix, OpenTelemetry).
- 6–10 years overall engineering experience, including 2–3 years focused explicitly on Generative AI / LLM applications.
Technologies you may work with
- AWS Bedrock, Anthropic Claude, Microsoft Copilot Studio, GitHub Copilot
- Model Context Protocol (MCP)
- GraphQL, Pinecone, Milvus, Qdrant, PGVector
- C#, .NET, LangSmith, Phoenix, OpenTelemetry
Location, schedule, and pay
- Work location: In person
- Expected hours: 40.0 per week
- Pay: USD 75.00 - 85.00 per hour
- Salary range: USD 75 - 85 per hourly
Benefits