Generative AI Engineer

GenAI / RAG Engineer

Experience: 6+ years (4+ years hands-on in GenAI/LLM applications)

Read this first!

1. Bring your experience, not your bot/AI tools to virtual interviews. Our process is built to spot the difference. Be authentic, we value that!
2. We detest Inflated or falsified resumes/payslips: Transparency and honesty are critical to us.
3. Lack of seriousness or commitment Give way to candidates genuinely interested in long‑term growth and contribution please!

What you'll build

Design, build, and scale production-grade AI systems for enterprise document intelligence and conversational analytics. The role involves building retrieval pipelines, multi-agent workflows, and production safeguards that ensure accurate, explainable, and reliable AI outputs in high-stakes enterprise contexts.

What you'll own

• End-to-end RAG pipelines: ingestion, chunking, embeddings, hybrid retrieval, and reranking
• Multi-agent workflows for validation, routing, and human-in-the-loop review
• Natural-language-to-query for analytics over enterprise data
• Failure handling: detecting low-confidence or no-match retrieval and escalating instead of hallucinating
• Evaluation (precision/recall, faithfulness, groundedness) on real annotated data

Must have

• Python, FastAPI, REST APIs
• RAG in production, not just POCs
• Azure AI Search, AWS OpenSearch, or equivalent
• LangChain/LangGraph or similar orchestration
• Experience with enterprise documents

Good to have

• Document comparison or analysis systems
• Human-in-the-loop and escalation design
• LLM cost and latency optimization