AI Engineer

Overview

AI Engineer & Solution Architect for working lead design and delivery of production GenAI (LLM/RAG and agentic) systems.

What you'll do

• Define technical standards, reusable patterns, and reference architecture for GenAI/agentic delivery.
• Manage and justify AI budget covering tooling, LLM/API spend, infrastructure costs, and licensing.
• Architect and build end-to-end GenAI/agentic solutions including RAG pipelines, LLM orchestration, and multi-agent workflows.
• Own full-stack solution architecture across backend services, APIs/microservices, data layer, and cloud infrastructure.
• Select and justify the technical stack (LLM providers, vector databases, orchestration frameworks) and codify team guidelines.
• Produce architecture artifacts (HLD/LLD, sequence diagrams, integration specs) and review designs for soundness.
• Implement evaluation, guardrails, and monitoring (hallucination checks, retrieval quality metrics, human-in-the-loop escalation).

What you'll need

• Hands-on production experience with LLMs and prompt engineering (OpenAI, Gemini, or equivalent).
• RAG architecture experience including chunking, embeddings, hybrid retrieval, and reranking.
• Agentic AI experience with tool-calling and planner/executor or multi-agent orchestration (LangChain/LangGraph or equivalent).
• Vector database experience (FAISS, Pinecone, pgvector, or equivalent) and semantic search implementation.
• ML/DL fundamentals to decide between classical models/fine-tuning vs LLM calls.
• Python as the primary language for AI/ML work.
• Strong software engineering background with architecture-level .NET/C# and/or Java (Spring/Spring Boot).
• Experience designing REST APIs and microservices with defined service boundaries and contracts.

Details

• Location: Hyderabad (DLF Cyber City), India.