Generative AI Engineer
Job Description
Data & Vector Engineering\nBuild and maintain scalable Vector Databases such as:\nPinecone\nWeaviate\nMilvus\nFAISS\npgvector\nOptimize document ingestion pipelines, including:\nChunking strategies\nEmbedding model selection\nMetadata filtering\nRetrieval ranking\nImprove retrieval precision and contextual relevance for drafting workflows.\nImplement retrieval evaluation and grounding mechanisms to reduce hallucinations.\n3. Deployment & MLOps (Local to Cloud)\nBridge local AI experimentation with scalable cloud deployment environments.\nDeploy AI services using:\nDocker\nKubernetes\nCloud infrastructure (AWS/GCP/Azure)\nManage:\nAPI latency\nRate limits\nToken optimization\nCost efficiency\nEstablish monitoring systems for:\nHallucination detection\nGroundedness metrics\nAI quality evaluation\nTracing and observability\nRequired Skills & Qualifications\nMandatory Experience\n3+ years of experience in:\nAI/ML Engineering\nBackend Engineering\nGenerative AI-focused product development\nHands-on expertise with:\nLangChain\nLlamaIndex\nStrong experience with:\nOpenAI API ecosystem\nOllama and local model runners\nProven experience implementing and optimizing:\nRAG pipelines\nVector databases\nEmbedding workflows\nAdvanced Python development skills using:\nFastAPI\nFlask\nAsynchronous programming\nExposure to:\nJIRA\nConfluence\nTechnical Stack\nModels\nOpenAI GPT-4 / GPT-4o\nOllama\nLlama 3\nMistral\nMixtral\nFrameworks & Tools\nLangChain\nLlamaIndex\nLangSmith\nDatabases\nPinecone\nChromaDB\npgvector\nInfrastructure & DevOps\nDocker\nKubernetes\nAWS / GCP / Azure\nGitHub Actions (CI/CD)\nWhat We Look For (The “Hacker” Mindset)\nProduction-Proven\nYou have successfully taken at least one GenAI product from:\nJupyter Notebook / local prototype to A live production environment with real users.\nProblem Solver\nYou understand the stochastic nature of LLMs and know how to:\nBuild guardrails\nReduce hallucinations\nImprove reliability\nEnsure grounded AI outputs\nArchitecture-First Thinking\nYou care deeply about:\nScalability\nLatency optimization\nToken efficiency\nCost management\nOutput quality\n\nPreferred Qualifications\nExperience building AI-powered drafting or document automation systems\nKnowledge of evaluation frameworks for LLM outputs\nFamiliarity with multi-agent systems and agent orchestration\nExperience with enterprise AI security and privacy considerations\nStrong debugging and performance optimization skills\nWhy Join Us?\nWork on cutting-edge Generative AI products with real-world impact\nBuild scalable AI systems from prototype to production\nCollaborate with a highly technical and innovation-driven team\nOpportunity to shape the future of AI-powered drafting and automation systems