AI Engineer

Role

Senior AI Engineer focused on designing and shipping production-grade LLM systems, autonomous agents, and retrieval-augmented generation (RAG) architectures. The role spans model engineering, production deployment, observability, and cross-functional collaboration with product, data, and backend teams.

Key Responsibilities

• Design and deploy autonomous AI agents using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or custom agent loops with tool-use, memory, and planning.
• Implement MCP (Model Context Protocol) servers/clients for standardized tool-calling across LLM applications.
• Build production RAG pipelines including chunking, embedding, hybrid retrieval, re-ranking, and grounded generation.
• Implement GraphRAG architectures using knowledge graphs (e.g., Neo4j, Microsoft GraphRAG) for multi-hop relational reasoning.
• Engineer LLM prompts, structured outputs, and evaluation pipelines across OpenAI, Anthropic Claude, Gemini, and open-source models.
• Fine-tune open-source models (LLaMA, Mistral, Phi) with LoRA/QLoRA for domain-specific tasks.
• Operate in AI-assisted development workflows (vibe coding) using Claude Code, GitHub Copilot, Cursor IDE, and related tools.
• Deploy and scale AI services on cloud platforms (AWS/GCP/Azure) with full observability, cost tracking, latency monitoring, and output quality monitoring.

Requirements

• 5+ years of AI/ML engineering experience (senior level) with hands-on experience in agents, RAG, GraphRAG, and related tooling.
• Strong proficiency in Python; experience with TypeScript/JavaScript.
• Experience with LLMs (OpenAI GPT variants, Anthropic Claude, Gemini, and open-source models).
• Experience building RAG/vector search solutions and working with vector DBs such as Pinecone, Weaviate, Qdrant, and pgvector.
• Experience with fine-tuning approaches (LoRA/QLoRA), PyTorch, HuggingFace Transformers, PEFT, and related tooling.
• Familiarity with MLOps and deployment tooling (MLflow, W&B, FastAPI, Docker, Kubernetes) and cloud ML services (AWS Bedrock/SageMaker, GCP Vertex AI, Azure ML).
• Required: Machine learning (4 years), Python (5 years), AI Agent (1 year).

Nice-to-have / Bonus

• Experience with A2A (Agent-to-Agent) protocols and multi-agent networks.
• Multimodal AI experience (vision-language, speech, image generation).
• Agentic security experience (prompt injection prevention, sandboxing, least-privilege tool access).
• Familiarity with LLM observability tools (LangSmith, Langfuse, Helicone).
• Open-source contributions, technical blogging, or conference talks.

Contract & Compensation

• Job type: Contractual / Temporary
• Contract length: 12 months
• Pay: ₹120,000.00 - ₹150,000.00 per month

Location & Work Arrangement

• Location listed: Bangalore City, Bengaluru, Karnataka (required)
• Work location: Remote

Application Question

• Explain your recent experience with AI Agent development.