AI Engineer (RAG & Multi-Agent Systems)

We are looking for an experienced AI/LLM Engineer to design, build, and maintain intelligent applications powered by Large Language Models (LLMs), embeddings, similarity search, vector databases, and multi-agent architectures.

The ideal candidate will build real-time AI systems such as chatbots, semantic search engines, recommendation systems, document intelligence platforms, MCP servers, and autonomous multi-agent workflows capable of tool usage and inter-agent communication.

You will own the end-to-end lifecycle of AI pipelines including data ingestion, embedding generation, vector storage, retrieval, LLM response orchestration, tool invocation, agent communication, and automated decision workflows.

Experience: 5-10+ Years overall, with over 1 year experience in building Agentic AI

Location: Bangalore

Employment Type: Full-Time

Key Responsibilities

• Design and implement embedding pipelines for text, documents, images, and structured data.
• Build and optimize semantic search and similarity search systems using vector databases.
• Integrate and manage vector databases such as:
• Pinecone, Weaviate, Milvus, FAISS, Chroma, OpenSearch Vector Engine, etc.

Develop LLM-powered applications for:

• Chatbots
• Q&A systems
• Recommendation engines
• AI agents and automation workflows
• Implement RAG (Retrieval Augmented Generation) pipelines with hybrid retrieval and reranking.
• Design and develop multi-agent architectures (planner-executor, supervisor-worker, tool-using agents).
• Build and deploy MCP (Model Context Protocol) servers to expose tools, memory, and external systems to LLM agents.
• Develop structured agentic workflows using frameworks like LangGraph, Strands, or similar orchestration engines.
• Implement multi-agent communication using A2A (Agent-to-Agent) protocols for collaborative reasoning and task execution.
• Design tool-calling pipelines and function-calling integrations.
• Fine-tune prompt strategies, memory handling, and system prompts for optimal LLM performance.
• Integrate LLM providers such as:
• OpenAI, Azure OpenAI, Anthropic, Google Gemini, Meta LLaMA, Mistral, etc.
• Build APIs and microservices for AI systems using:
• Python / Java / Node.js / Spring Boot / FastAPI
• Implement similarity scoring, ranking, filtering, and metadata-based retrieval.
• Monitor, optimize, and scale vector search performance.
• Optimize LLM cost, latency, caching, and response validation strategies.
• Implement AI safety mechanisms, hallucination reduction, guardrails, and evaluation pipelines.
• Work closely with product, frontend, and data teams.
• Deploy AI workloads on AWS, Azure, GCP, or OCI.
• Maintain CI/CD pipelines for AI services.

Required Skills & Qualifications

Mandatory Core AI, LLM & Agentic Skills

• Strong understanding of:
• Embeddings
• Vector similarity search
• Cosine similarity, dot product, ANN indexing
• RAG architectures

Hands-on experience with:

• LangChain / LlamaIndex / Semantic Kernel / Spring AI
• Experience building multi-agent systems and agent orchestration pipelines
• Experience building MCP servers for tool and context exposure
• Experience with LangGraph / Strands or similar agent workflow orchestration tools
• Experience implementing A2A (Agent-to-Agent) communication patterns
• Proficient in prompt engineering, memory management, and LLM orchestration
• Experience with at least one Vector Database

Programming & Backend

• Strong proficiency in Python / Java / JavaScript / TypeScript
• API development using FastAPI, Flask, Spring Boot, or Node.js
• Strong understanding of REST APIs, async processing, event-driven architectures
• Experience building microservices for AI agents.

Data & Storage

• Experience with:
• PostgreSQL, MySQL, MongoDB
• Object storage (S3, OCI, Azure Blob)
• Data preprocessing, chunking strategies, tokenization optimization
• Knowledge of metadata filtering and hybrid search

Cloud & DevOps (Good to Have)

• Docker & Kubernetes
• CI/CD pipelines (Jenkins, GitHub Actions, GitLab, Bitbucket)
• Monitoring with Prometheus, Grafana, OpenTelemetry
• Experience deploying scalable AI inference pipelines

Good to Have (Preferred Skills)

• Deep experience with Agentic AI frameworks
• Knowledge of Tool Calling / Function Calling
• Experience with workflow engines and orchestration graphs
• Experience with Speech-to-Text, Vision models
• Fine-tuning, LoRA, PEFT experience
• Knowledge of AI security, governance & data privacy
• Experience building autonomous AI systems with memory + tools
• Experience designing distributed agent architectures

Use Cases You Will Work On

• AI chatbots for customer support
• Semantic document search
• Knowledge-base Q&A systems
• Multi-agent workflow automation
• Intelligent AI copilots
• Automated ticket triaging
• AI assistants for developers and operations
• Collaborative agent systems using A2A protocols
• MCP-based tool-integrated AI systems