AgenticAI Forward Deployed Engineer| Onsite

Role Summary

We are looking for a Lead Forward Deployed AI Engineer with 7+ years of experience to design, build, deploy, and scale production-grade AI solutions for enterprise clients. This is a hands-on full-stack engineering role that combines client-facing solutioning, Agentic AI, RAG, MCP/tool integrations, cloud deployment, and production ownership.

The ideal candidate should be able to work directly with stakeholders, understand business problems, architect practical AI solutions, write production code, deploy applications, and support systems after rollout. Forward deployed AI roles typically require end-to-end ownership from discovery and scoping through implementation, production rollout, and customer adoption.

Key Responsibilities

• Work with clients and internal teams to understand business requirements and identify high-impact AI use cases.

• Architect and build AI solutions using LLMs, Agentic AI, RAG, MCP/tool-calling, APIs, and enterprise integrations.

• Develop full-stack applications, including backend services, APIs, frontend interfaces, dashboards, and workflow tools.

• Build RAG pipelines including document ingestion, chunking, embeddings, vector search, retrieval, reranking, and response grounding.

• Design and implement agentic workflows using frameworks such as LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI, or similar.

• Integrate AI agents with enterprise systems, databases, APIs, document repositories, and business applications.

• Deploy and operate AI applications using Docker, CI/CD, cloud services, logging, monitoring, and production observability.

• Implement security and governance patterns such as RBAC, audit logging, prompt injection protection, data access controls, and safe tool execution.

• Own delivery from prototype to production, including debugging, performance tuning, stakeholder communication, and adoption support.

• Create reusable frameworks, components, and engineering patterns to accelerate future AI implementations.

Required Qualifications

• 7+ years of software engineering experience, including experience leading technical delivery.

• Strong hands-on coding experience in Python and modern full-stack development.

• Experience building production-grade APIs, backend services, frontend applications, and integrations.

• Hands-on experience with LLM applications, Agentic AI, RAG, or enterprise GenAI systems.

• Experience with at least one agent framework; LangGraph is strongly preferred.

• Strong understanding of embeddings, vector search, retrieval quality, chunking, reranking, and grounding.

• Experience deploying applications using Docker, CI/CD pipelines, cloud services, logging, and monitoring.

• Ability to translate ambiguous business problems into working technical solutions.

• Strong communication skills and comfort working directly with clients, engineers, product teams, and leadership.

• Proven ability to architect, code, deploy, troubleshoot, and deliver complete solutions end to end.

Preferred Qualifications

• Experience with MCP, function-calling, tool-calling, or custom tool/server integrations.

• Experience with vector databases or search platforms such as Azure AI Search, OpenSearch, Elasticsearch, Pinecone, Weaviate, Milvus, FAISS, or pgvector.

• Experience with cloud platforms such as Azure, AWS, or GCP.

• Experience with Kubernetes, API gateways, secrets management, and production infrastructure.

• Experience with AI evaluation tools such as RAGAS, DeepEval, Promptfoo, OpenTelemetry, or custom evaluation pipelines.

• Experience implementing guardrails, hallucination mitigation, PII handling, and enterprise security controls.

• Prior consulting, client-facing engineering, solution delivery, or forward deployed engineering experience.