Forward Deployed AI Engineer

• Understand the business need before building and take solutions from discovery through production.
• Design, build, deploy and continuously improve enterprise-grade agentic AI applications.
• Build agents that reason across multiple steps, call tools and APIs, manage context, handle exceptions and support human-in-the-loop workflows.
• Design and implement RAG pipelines covering ingestion, chunking, embeddings, vector search, retrieval tuning, grounding and source traceability.
• Build MCP-based integrations and connect agents to backend systems through REST/OpenAPI, webhooks and event-driven patterns with secure authentication.
• Apply structured LLM patterns including tool calling, schema-validated outputs, retries, fallbacks and guardrails.
• Coordinate with Business Product Owners, AI Value Architects and other squads.
• Own end-to-end delivery of significant AI use cases and set the pace on quality, evaluation and reliability.

Requirements:

• Degree in Computer Science, Software Engineering, Data Science, AI/ML or a related technical field, or equivalent practical experience.
• 5+ years building production-grade software, including 3+ years with GenAI and LLMs.
• Minimum 1 year of hands-on Agentic AI experience with a proven record of taking agentic solutions to production.
• Hands-on experience or strong working knowledge of MCP for connecting agents to tools, systems, APIs and data.
• Experience with async programming, FastAPI, Pydantic, Git, CI/CD, testing, error handling and logging.
• Experience with at least one agent framework or enterprise AI platform such as Lang Graph, Semantic Kernel, CrewAI, Auto Gen, OpenAI Agents SDK, Microsoft Foundry, Amazon Bedrock Agent Core or Google Vertex/Gemini.
• Experience with vector databases/search platforms such as Azure AI Search, pgvector, Pinecone, Weaviate or Open Search.