AI Forward Deployed Engineer (AI FDE)

The Role As an AI Forward Deployed Engineer (AI FDE), you will work directly with clients to turn complex business problems into AI systems that run in production. Combining hands-on engineering with consulting, you will scope problems, build practical solutions, and ensure they deliver measurable value. You will bridge the gap between client requirements and Steinn Labs' engineering team. Your insights from client engagements will also help shape reusable products and engineering playbooks. Key Responsibilities - Work on-site at the client's office in Pune, embedded with their team. - Understand client workflows and identify opportunities where AI can deliver value. - Build and deploy LLM applications, including RAG systems, agents, and tool integrations. - Integrate AI systems with enterprise software, including ERP, CRM, databases, and internal APIs. - Set up evaluations, guardrails, and monitoring to ensure reliable AI systems. - Act as the bridge between the client and Steinn Labs' engineering team. - Conduct client demos and maintain up-to-date technical documentation. Must-Have Requirements - 4–8 years of software engineering experience, including at least 1.5 years building LLM/GenAI applications used in production. - Strong Python programming skills, with experience in FastAPI, Flask, or Django. - Hands-on experience with Retrieval-Augmented Generation (RAG), embeddings, and vector databases such as pgvector, Qdrant, Pinecone, Weaviate, or similar. - Experience with agent frameworks such as LangGraph, LangChain, or LlamaIndex. - Experience using LLM APIs from OpenAI, Anthropic, or Gemini, or working with open-source models. - Strong understanding of REST APIs and SQL, with hands-on experience using Docker. - Experience with at least one cloud platform: AWS, Azure, or GCP. - Client-facing experience in requirement gathering, conducting demos, and explaining technical trade-offs to non-technical stakeholders. - Based in Pune or willing to relocate, with the ability to work full-time from the client's office. Good-to-Have Requirements - Previous experience as a Forward Deployed Engineer, Solutions Engineer, or Consultant at an AI startup or IT services firm. - Experience with LLM evaluation tools such as Ragas, DeepEval, LangSmith, or Langfuse. - Experience with self-hosted models such as vLLM or Ollama, or fine-tuning LLMs. - Knowledge of LLM security, prompt injection, guardrails, and the OWASP Top 10 for LLMs. - TypeScript or React experience for building quick internal user interfaces. - Domain exposure in BFSI, manufacturing, aviation, or building automation. - Experience with enterprise integrations such as SAP, Salesforce, or similar platforms.