Forward Deployed Engineer – GenAI

About the role

We are looking for a Forward Deployed Engineer to build production‑grade generative AI applications, including LLM‑powered features, copilot experiences, and enterprise search solutions. You will work closely with client engineers to translate business needs into concrete GenAI specifications.

Key responsibilities

• Design and implement Retrieval‑Augmented Generation pipelines, including chunking, embedding selection, hybrid retrieval, re‑ranking and GraphRAG where structured retrieval is required.
• Fine‑tune and adapt large language models using LoRA/QLoRA techniques and manage versioned production prompts.
• Integrate LLM APIs (OpenAI, Anthropic, Azure OpenAI) and open‑source model endpoints with authentication, rate‑limiting and cost controls.
• Instrument applications for evaluation with output logging, quality scoring and human‑feedback loops, and optimise latency and token cost through caching, batching and model routing.
• Communicate technical trade‑offs such as cost, latency and accuracy to non‑technical product stakeholders.

Required profile

• 4–8 years of software engineering experience, including 1–3 years building GenAI/LLM applications.
• Strong Python programming skills and experience with orchestration frameworks such as LangChain or LlamaIndex.
• Hands‑on experience with vector databases (Pinecone, Weaviate, pgvector) and graph‑database tooling (Neo4j) where relevant.
• Understanding of LLM failure modes and ability to design mitigations.
• Comfortable collaborating directly with client engineers during embedded delivery.

Required skills

• Python
• LangChain or LlamaIndex
• Vector databases: Pinecone, Weaviate, pgvector
• Graph databases: Neo4j
• LLM fine‑tuning: LoRA, QLoRA
• LLM APIs: OpenAI, Anthropic, Azure OpenAI
• Cloud GenAI platforms: Microsoft Azure AI Foundry, AWS Bedrock, Google Vertex AI
• API design with authentication, rate limiting and streaming
• Prompt versioning and LLMOps tools: LangSmith, Weights & Biases