Design, develop, and deliver innovative AI-powered solutions that showcase the practical value of generative AI and large language models (LLMs) for clients.
Requirements
- Experience with an object-oriented programming language such as Python, and applying it to AI/ML solution development
- Experience designing and implementing generative AI applications with LLMs
- Experience with AI orchestration frameworks such as LangChain, and multi-provider integration
- Experience building secure and scalable deployments on cloud platforms such as AWS
- Knowledge of data processing techniques for AI, including text, audio, and multi-modal
- Experience with agent frameworks and interoperability standards, including MCP, A2A, and LangServe
- Experience with model fine-tuning, prompt tuning, or domain adaptation
Responsibilities
- Design adaptable AI application architectures that support multiple providers, modalities, and deployment modes.
- Build modular and reusable components and frameworks for rapid creation of new AI-powered capabilities.
- Integrate LLMs, embeddings, and retrieval-augmented generation (RAG) patterns into production-ready systems.
- Apply prompt engineering, orchestration frameworks such as LangChain, and agent-based architectures such as MCP and A2A, to enable goal-directed autonomy with guardrails, observability, and human oversight, including planning, tool use, and delegation.
- Architect and optimize AI applications for various deployment scenarios, including embedded, offline-capable, and hybrid solutions.
- Implement model evaluation, benchmarking, and optimization for cost, latency, and accuracy.
- Develop pipelines for preparing, chunking, and enriching structured or unstructured data for AI workflows.
Other
- 5+ years of experience with software engineering
- 2+ years of experience in AI or ML-focused roles
- Ability to engage both technical and business audiences
- Secret clearance
- Bachelor’s degree in a CS or Engineering field
