Forward Deployed Engineer – Generative AI

About the role

We are looking for a Forward Deployed Engineer specialized in Generative AI to build production‑ready LLM‑powered features, retrieval‑augmented generation (RAG) pipelines, and enterprise search solutions. You will work closely with client engineering teams to translate business needs into robust AI applications.

Key responsibilities

• Design and implement GenAI applications, including copilot/chat experiences and enterprise search.
• Build and optimise RAG pipelines: 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 endpoints with authentication, rate‑limiting, and cost controls.
• Instrument applications for evaluation, logging, quality scoring, and human‑feedback loops.
• Optimise latency and token cost through caching, batching, and model routing.
• Communicate technical trade‑offs to non‑technical stakeholders and document architecture decisions.

Required profile

• 4–8 years of software engineering experience, with 1–3 years focused on GenAI/LLM application development.
• Strong Python programming skills.
• Ability to work directly with client engineers and collaborate with architects, data scientists, and QA teams.
• Clear technical writing for non‑technical audiences.

Required skills

• Python
• LangChain, LlamaIndex (or similar orchestration frameworks)
• Vector databases: Pinecone, Weaviate, pgvector
• Graph databases: Neo4j (when relevant)
• LLM APIs: OpenAI, Anthropic, Azure OpenAI
• Model fine‑tuning: LoRA, QLoRA
• Enterprise GenAI platforms: Microsoft Azure AI Foundry, AWS Bedrock, Google Vertex AI
• API design and integration (auth, rate limiting, streaming)
• Prompt‑versioning and LLMOps tools: LangSmith, Weights & Biases