Gravity- AI Engineer

Job Description - AI Engineer
Job Title: AI Engineer
Location: Mumbai
Employment Type: Full-time
Experience: 3–5+ years relevant experience
Role Overview
We are looking for an AI Engineer with hands-on experience in building and deploying Generative AI, LLM,
RAG, and machine-learning solutions. The role involves designing production-grade AI applications, working
with structured and unstructured data, integrating LLMs with backend systems, evaluating model
performance, and deploying AI services.
Experience working on banking, financial services, compliance, or enterprise AI applications would be an
advantage.
Key Responsibilities
• Design, develop, and maintain LLM and Generative AI applications.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines involving document ingestion,
chunking, embeddings, vector search, retrieval, and response generation.
• Work with vector databases such as Qdrant and relational databases such as PostgreSQL.
• Develop backend AI services and APIs using Python and Django/REST APIs.
• Build LLM-based solutions for information extraction, classification, summarization, document
processing, and question answering.
• Design and implement LLM evaluation frameworks, including retrieval evaluation, response quality,
groundedness, accuracy, and data-quality checks.
• Develop and maintain synthetic-data generation and validation pipelines for AI/ML use cases.
• Build secure Natural Language to SQL and database-interaction solutions.
• Work with embedding models and traditional ML models for classification and routing problems.
• Deploy and integrate open-source and hosted LLMs into production applications.
• Perform LLM inference optimization, API integration, logging, monitoring, and performance
troubleshooting.
• Work with Docker and cloud/deployment environments for AI services.
• Collaborate with backend, product, and domain teams to convert business requirements into AI
solutions.
• Maintain technical documentation and ensure proper knowledge transfer for developed systems.

Required Technical Skills
• Strong Python programming skills
• Generative AI and Large Language Models
• RAG architecture and implementation
• Prompt engineering
• Embeddings and semantic search
• Vector databases — preferably Qdrant
• PostgreSQL / SQL
• Django / REST API development
• Machine Learning fundamentals
• LLM evaluation and testing
• Docker
• Git/version control
Good to Have
• Experience with Ollama, vLLM or other open-source LLM serving frameworks
• GPU-based LLM deployment and inference optimization
• BM25 / hybrid search
• LoRA / model or embedding fine-tuning
• Kubernetes and AWS/cloud deployment
• API governance and enterprise AI systems
• Experience working with banking/compliance documents
• Experience with PII/sensitive-data handling and AI security
• Experience with agentic AI, tool calling, MCP or AI workflow orchestration
Qualifications
• Bachelor's/Master's degree in Computer Science, IT, AI/ML, Data Science, or a related field.
• 3–5+ years of software engineering, machine-learning, or AI engineering experience.
• Demonstrable experience building end-to-end AI/LLM applications, preferably deployed in production.
• Strong problem-solving, debugging, communication, and documentation skills.

Ideal Candidate
Someone who can independently take an AI requirement from:
Problem → Data → Prototype → Evaluation → API/Integration → Deployment → Monitoring
rather than someone whose experience is limited to calling an LLM API or creating basic prompts.