Description:
We are looking for a hands-on Forward Deployed AI Engineer to design, build, deploy, and continuously improve enterprise-grade AI and agentic AI solutions.
The role focuses on developing production-ready AI applications that use LLMs, agents, RAG, MCP, enterprise APIs, and modern cloud technologies. The engineer will work across the complete AI application lifecycle, from solution design and development through deployment, testing, monitoring, and continuous improvement.
Key Responsibilities
- Design, build, deploy, and continuously improve enterprise-grade Agentic AI applications using modern GenAI technologies.
- Build AI agents that can reason across multiple steps, invoke tools and APIs, manage context, handle exceptions, and support human-in-the-loop workflows.
- Design and implement RAG pipelines, including document ingestion, chunking, embeddings, vector search, retrieval optimization, grounding, and source traceability.
- Build MCP-based integrations to connect AI agents with enterprise tools, systems, APIs, and data sources.
- Integrate agents with backend systems using REST/OpenAPI APIs, webhooks, queues, and event-driven architectures.
- Implement structured LLM patterns including tool calling, schema-validated outputs, retries, fallbacks, context management, and guardrails.
- Develop reliable AI workflows using agent frameworks and orchestration patterns such as LangGraph, Semantic Kernel, CrewAI, AutoGen, OpenAI Agents SDK, or equivalent technologies.
- Design and implement multi-agent systems and agent-to-agent communication patterns where appropriate.
- Build AI solutions with appropriate security, privacy, access control, auditability, responsible AI, and governance mechanisms.
- Implement testing and evaluation strategies for AI systems, including golden datasets, regression testing, evaluation metrics, validation workflows, and feedback loops.
- Implement observability, logging, monitoring, versioning, and performance tracking for production AI applications.
- Optimize AI applications for accuracy, reliability, latency, scalability, and cost.
- Develop reusable components, APIs, tools, and AI capabilities that can be consumed across multiple applications.
- Deploy AI applications using modern cloud-native technologies, containers, CI/CD pipelines, and monitoring platforms.
- Collaborate with engineering, product, data, and AI teams to deliver production-ready AI solutions.
- Stay current with emerging developments in Agentic AI, LLMs, MCP, RAG, AI evaluation, and AI engineering practices.