Senior AI platform Engineer.
Location : Bangalore , Hybrid Model (3 days work from office in a week)
About The Role
We are looking for a Senior AI Platform Engineer to join our AI team and help build a next-generation AI-powered customer experience platform. This role focuses on designing, developing, and maintaining production-grade AI systems, including LLM integrations, RAG pipelines, AI agent workflows, and supporting infrastructure.
You will work closely with architects and cross-functional teams to transform AI capabilities into scalable, reliable platform features. This role requires strong hands-on experience with production AI systems, prompt engineering, and LLM integration patterns in a fast-paced environment.
Key Responsibilities
- Design, build, and maintain AI agent workflows and orchestration patterns (e.g., LangGraph)
- Develop and optimize production-grade RAG systems (chunking, retrieval pipelines, embeddings, response quality)
- Implement and manage LLM API integrations with retry logic, fallbacks, rate limiting, and cost optimization
- Build advanced prompt engineering solutions (system prompts, few-shot learning, structured outputs, versioning)
- Develop input validation, output filtering, and AI safety layers
- Implement AI observability and evaluation frameworks (tracing, regression testing, quality checks)
- Build data ingestion pipelines for AI systems (document processing, embeddings, vector storage)
- Collaborate with product and architecture teams to deliver scalable AI solutions
- Write clean, testable, and production-ready code (unit, integration, and AI-specific tests)
- Contribute to technical documentation, design docs, and operational runbooks
Must-Have Skills & Experience
- 5+ years of software development experience
- Hands-on experience building AI/ML or LLM-powered systems in production
- Strong understanding of LLM fundamentals (tokens, embeddings, context windows, temperature, similarity search)
- Experience with RAG systems (indexing, chunking strategies, retrieval methods)
- Strong prompt engineering expertise (few-shot, structured outputs, iterative improvements)
- Experience with AI orchestration frameworks (LangGraph, LangChain, or similar)
- Hands-on experience with vector databases (pgvector, Pinecone, Qdrant, Weaviate, etc.)
- Strong proficiency in Python
- Experience working with LLM APIs (OpenAI, Claude, or similar)
- Understanding of AI safety concepts (prompt injection, jailbreaking, mitigation strategies)
- Experience with cloud platforms (AWS preferred) and containerization (Docker, Kubernetes)
- Strong analytical and problem-solving skills
Good-to-Have Skills
- Experience with AI observability tools (LangSmith, LangFuse)
- Familiarity with Model Context Protocol (MCP) or similar integration patterns
- Understanding of fine-tuning vs prompt-based approaches
- Programming experience in Java
- Experience with event-driven systems (Kafka, RabbitMQ)
- Telecom domain knowledge (billing, CRM, lifecycle management)
- Experience building customer-facing AI products
- Backend development experience (Go, Node.js, Java microservices)
