Job Title

About the RoleWe are hiring a 3D Reconstruction & Generative AI Engineer to build an end-to-end system that can generate high-precision 3D jewellery models from images and text prompts.This role goes beyond classical CV — you will design systems that combine:3D reconstruction (multi-view / single-view)Generative AI (text-to-3D / image-to-3D)RAG pipelines for design retrieval and conditioningThe final output must be manufacturing-grade meshes suitable for gold casting / 3D printing.Key Responsibilities3D Reconstruction & GeometryBuild pipelines for:Multi-view → 3D mesh reconstructionSingle-view → 3D with learned priorsImplement:Point cloud generation, fusion, and meshingSurface reconstruction and refinementEnsure:High geometric accuracy (sub-mm level)Clean topology (watertight meshes)Generative AI (Core Focus)Develop and fine-tune models for:Text-to-3D generationImage-to-3D generationWork with:Diffusion models (2D → 3D lifting)NeRF / Gaussian Splatting-based methodsLatent 3D representationsIntegrate:Style control.Conditional generation (user constraints)RAG (Retrieval-Augmented Generation) SystemsBuild RAG pipelines for:Retrieving existing designs / CAD assetsConditioning generative models with reference designsDesign:Embedding pipelines (image + text embeddings)Vector databases for design searchEnable:“Generate similar to this design” workflowsHybrid pipelines:Retrieval → conditioning → generation → refinementOptimize for:Low-latency retrievalHigh semantic relevanceModel Optimization & DeploymentOptimize models for:GPU efficiency (multi-GPU setups)Batch inference pipelinesDeploy:APIs for generation (image/text → 3D)Scalable backend systemsPost-Processing & CAD ReadinessImplement:Mesh cleanup (hole filling, smoothing)Topology correctionConversion to CAD-friendly formats (STL/STEP)Ensure outputs are:Print-readyStructurally valid for castingRequired SkillsCoreStrong experience in Python + PyTorchSolid understanding of:3D geometry (meshes, point clouds, SDFs)Multi-view geometry & camera calibrationRendering and differentiable renderingExperience with:PyTorch3D / Open3D / Trimesh3D reconstruction pipelines (SfM, MVS, NeRF)Generative AIHands-on experience with:Diffusion models (Stable Diffusion, latent diffusion)GANs / 3D generative modelsUnderstanding of:Text-to-image / text-to-3D pipelinesConditioning and prompt engineeringRAG & LLM SystemsExperience building:RAG pipelines (retrieval + generation)Familiarity with:Vector databases (e.g., FAISS, Milvus)Embedding models (CLIP, multimodal embeddings)Ability to:Combine structured (CAD) + unstructured (images/text) dataDesign semantic search systemsPreferred / Bonus SkillsExperience in:Jewellery design / CAD workflowsBlender / MeshLab / Rhino / Fusion 360Familiarity with:Vision-language modelsGrounding models (e.g., object-aware generation)Experience with:Multi-GPU training (important for your setup)Diffusion + 3D hybrid pipelinesExpected OutcomesBuild a system capable of:Text/Image → high-quality 3D jewelleryRetrieval-assisted generation (RAG-powered design system)Deliver:Production-ready meshesConsistent design quality across variationsCandidate Profile2–6+ years in:Computer Vision / Generative AI / 3D GraphicsStrong in both:Research understandingProduction deploymentNice-to-Have Project ExperienceText-to-3D systemsRAG-based generative pipelinesHigh-detail reconstruction (jewellery / mechanical parts)CAD-integrated AI systemsCompensationCompetitive (based on experience and depth in GenAI + 3D)BETWEEN 4-8 LPA, BASED ON PERFORMANCE.