Generative AI Engineer Position
We are seeking a skilled Generative AI Engineer to join our team. As a key member of our engineering team, you will be responsible for designing, building, and optimizing our core intelligence systems.
- Knowledge Extraction : Develop pipelines that capture work specifications, decisions, and requirements from AI conversations – distinguishing signals from noise.
- GraphRAG Development : Implement and optimize graph-based retrieval systems for precise, low-latency context delivery.
- Prompt & Agent Design : Engineer and maintain advanced multi-step prompts and workflows for extraction, synthesis, and retrieval.
- Evaluation Frameworks : Develop LLM-as-judge systems and rubrics to measure extraction quality, contextual accuracy, and reliability.
- Model Optimization : Apply fine-tuning, adapters, or lightweight training where beneficial; manage data quality and ontology standards.
- Production Deployment : Ensure systems run efficiently at scale (latency, cost, monitoring, reliability).
Must-Have Qualifications :
3+ years building production LLM or generative AI systems.Strong Python engineering skills.Hands-on with RAG systems, embeddings, and vector databases.Proven expertise in prompt engineering and structured information extraction.Experience with LLM evaluation frameworks & optimization (accuracy, latency, cost).Practical exposure to fine-tuning methods (LoRA, adapters).Familiarity with cloud AI services.Based in India.Preferred Qualifications :
Experience with GraphRAG / Neo4j.Familiarity with LangChain, LlamaIndex, or similar frameworks.Knowledge graphs and ontology design.Experience building multi-agent LLM systems.Why Work With Us :
We're dedicated to eliminating the friction of context management by giving every AI you use full knowledge of your projects, preferences, and past work. As our Generative AI Engineer, you'll be building the intelligence layer that transforms how humans work with AI.
You'll own systems that sit at the core of the product, work directly with founders, and see your work ship to real users in days, not months.