Forward Deployed AI Engineer

Overview

This role involves understanding business requirements thoroughly to develop and implement AI solutions that progress from ideation to full production. The focus is on creating advanced, enterprise-grade agentic AI systems capable of multi-step reasoning, API/tool integration, context management, exception handling, and enabling human oversight in workflows.

Key Responsibilities

• Translate business needs into effective AI solutions and deliver them through production deployment.
• Architect, develop, deploy, and constantly refine sophisticated agentic AI applications targeted for enterprise use.
• Create AI agents that process multiple steps of reasoning, invoke external APIs and tools, manage contextual information, handle errors, and incorporate human-in-the-loop processes.
• Design and execute Retrieval Augmented Generation (RAG) pipelines including components like data ingestion, chunking, embedding generation, vector search, retrieval optimization, grounding, and traceability.
• Develop integrations based on the MCP framework connecting AI agents with backend systems via REST/OpenAPI endpoints, webhooks, and event-driven models while maintaining stringent security through authentication.
• Utilize structured Large Language Model (LLM) patterns such as tool invocation, schema-validated responses, error retries, fallback mechanisms, and operational guardrails.
• Collaborate with Business Product Owners, AI Value Architects, and cross-functional teams to align on project objectives.
• Lead comprehensive AI use case deliveries, emphasizing quality assurance, performance evaluation, and system reliability.

Qualifications and Experience

• Degree in Computer Science, Software Engineering, Data Science, Artificial Intelligence/Machine Learning, or a related technical discipline; or comparable professional experience.
• Over five years of experience in developing production-level software, with at least three years specializing in Generative AI and Large Language Models.
• At least one year of practical, hands-on experience developing and deploying agentic AI solutions successfully in production environments.
• Experience with MCP frameworks for linking AI agents to various tools, systems, APIs, and data sources.
• Proficiency in Python programming, complemented by working knowledge of TypeScript or JavaScript; familiarity with Java or C# is advantageous.
• Experience in asynchronous programming paradigms and tools such as FastAPI, Pydantic, and version control with Git, including CI/CD workflows, testing methodologies, error handling, and logging best practices.
• Hands-on experience with agent frameworks or enterprise AI platforms like LangGraph, Semantic Kernel, CrewAI, AutoGen, OpenAI Agents SDK, Microsoft Foundry, Amazon Bedrock AgentCore, or Google Vertex/Gemini.
• Familiarity with vector database and search technologies such as Azure AI Search, pgvector, Pinecone, Weaviate, or OpenSearch.