AI ML Engineer
Chennai, India · Full-time
- Posted 1w ago
- From Neurealm’s careers page
- Location
- Chennai, India
- Type
- Full-time
- Level
- Lead
- Experience
- 8+ years
- Department
- Engineering
This role is no longer on Neurealm’s careers page.
Let the right jobs find you
In your inbox every Wednesday and SaturdayPersonalised suggestions from verified career pages, matched to your role, location, level and skills.
About the role
Role Summary
We are seeking a Senior AI/ML Engineer with deep expertise in Generative AI, Intelligent Document Processing, Large Language Models (LLMs), Vector Databases, and AI solution engineering. The ideal candidate will have hands-on experience designing and implementing enterprise-grade AI solutions leveraging Google Document AI, Retrieval Augmented Generation (RAG), Vector Search, LLM orchestration frameworks, and continuous learning feedback loops.
This role will be instrumental in developing AI-powered document intelligence solutions, enterprise knowledge assistants, semantic search platforms, and business process automation capabilities.
Key Responsibilities
Generative AI Solution Development
- Design, build, and deploy enterprise Generative AI solutions.
- Develop AI-powered assistants, copilots, and knowledge retrieval systems.
- Implement Retrieval Augmented Generation (RAG) architectures.
- Integrate Large Language Models (LLMs) into enterprise applications.
- Optimize prompts, retrieval strategies, and grounding mechanisms.
- Build scalable AI services supporting production workloads.
Intelligent Document Processing
- Design document ingestion and processing pipelines using Google Document AI.
- Develop solutions for OCR, Document Classification, Data Extraction, Entity Recognition, Form Processing, Invoice Processing, and Contract Intelligence.
- Build automated workflows to process structured and unstructured documents.
Vector Database & Semantic Search
- Design and implement vector search solutions.
- Generate and manage embeddings for enterprise knowledge repositories.
- Build semantic search and contextual retrieval frameworks.
- Optimize chunking, indexing, and ranking mechanisms.
- Manage large-scale vector indexes and retrieval systems.
Continuous Learning & AI Optimization
- Implement Human-in-the-Loop (HITL) feedback mechanisms.
- Design continuous learning pipelines to improve AI responses.
- Monitor AI model performance and user satisfaction metrics.
- Build evaluation frameworks for Hallucination Detection, Response Quality, Retrieval Accuracy, and Grounding Effectiveness.
- Drive model refinement through feedback loops and usage analytics.
AI Platform Engineering
- Develop scalable AI APIs and microservices.
- Integrate AI services with enterprise applications.
- Collaborate with Data Engineers and Full Stack Developers.
- Support cloud-native AI deployments.
- Establish AI governance, monitoring, and operational best practices.
Skills they ask for
Pick one to see other roles that ask for it.
About Neurealm
AI-powered digital engineeringNeurealm engineers AI-powered solutions at scale, from Physical AI to Agentic AI, combining engineering, data and technology to transform enterprises.
See all 1 roles at NeurealmMore roles at Neurealm
See all 1Let the right jobs find you
In your inbox every Wednesday and SaturdayPersonalised suggestions from verified career pages, matched to your role, location, level and skills.