Forward Deployed Engineer - Generative AI

About the role

We are looking for a Forward Deployed Engineer to build production‑ready generative AI applications. You will work closely with client engineers to translate business needs into LLM‑powered features, RAG pipelines, and enterprise search solutions.

Key responsibilities

• Design and implement RAG pipelines, including chunking, embedding selection, hybrid retrieval, re‑ranking and GraphRAG where needed.
• Fine‑tune and adapt models using LoRA/QLoRA and manage prompt versioning.
• Integrate LLM APIs (OpenAI, Anthropic, Azure OpenAI) and open‑source model endpoints with authentication, rate‑limiting and cost controls.
• Instrument applications for evaluation, logging, quality scoring and human‑feedback loops.
• Optimize latency and token cost through caching, batching and model routing strategies.
• Collaborate with Agentic AI Architects and Data Scientists on shared components and document architecture decisions.

Required profile

• 4–8 years of software engineering experience, with 1–3 years building GenAI/LLM applications.
• Strong Python programming skills and experience with orchestration frameworks such as LangChain or LlamaIndex.
• Understanding of LLM failure modes and ability to design mitigations.
• Comfortable working directly with client engineers in an embedded delivery model.

Required skills

• Python
• LangChain, LlamaIndex (or equivalent)
• Vector databases: Pinecone, Weaviate, pgvector
• Graph databases: Neo4j
• Model fine‑tuning: LoRA, QLoRA
• LLM APIs: OpenAI, Anthropic, Azure OpenAI
• Enterprise GenAI platforms: Azure AI Foundry, AWS Bedrock, Google Vertex AI
• API design, authentication, rate limiting, streaming responses
• LLMOps tools: LangSmith, Weights & Biases