Agentic AI Engineer

Whereuelevate; Dadri; On-site; INR 1,200,000 - 2,400,000; Full time

Job summary

Whereuelevate is seeking a hands-on Gen AI / Agentic AI Engineer to build and deploy intelligent AI agents capable of reasoning, task execution, and workflow automation. You will design agentic architectures, integrate LLMs with tools and APIs, and develop RAG pipelines.

You will collaborate with cross-functional teams to deliver real world AI‑driven applications, focusing on scalable, reliable, and cost‑efficient solutions while ensuring safety and performance.

Qualifications

• Hands-on Python programming experience (required).
• Experience with LLMs and AI agent frameworks (required).
• Experience building tool-calling agents and workflow-driven AI systems (required).
• Knowledge of RAG, embeddings, vector databases (FAISS, pgvector, Quadrant) (required).
• API integration experience (REST, Webhooks, OAuth) (required).
• Understanding of prompt engineering, agent memory, and evaluation (required).
• Experience with FastAPI for AI services (preferred).
• Familiarity with cloud platforms (Azure / AWS / GCP) (preferred).

Responsibilities

• Design and implement Agentic AI systems (planner–executor, tool‑using agents, multi‑agent workflows).
• Build agents capable of reasoning, task decomposition, memory, and decision‑making.
• Integrate LLMs with tools, APIs, databases, and enterprise systems.
• Develop RAG pipelines, long‑term memory, and context management for agents.
• Orchestrate agents using frameworks like LangGraph, LangChain, CrewAI, AutoGen, LangFlow.
• Implement human‑in‑the‑loop workflows and safety guardrails.
• Optimize for latency, cost, reliability, and scalability.
• Collaborate with product, backend, and frontend teams to ship real use cases.

Skills

Python

LLMs

Tool-calling agents

RAG

APIs integration

Prompt engineering

FastAPI

Cloud platforms (Azure AWS GCP)

Job description

We are seeking a hands-on Gen AI / Agentic AI Engineer to build and deploy intelligent AI agents capable of reasoning, task execution, and workflow automation. The role involves developing agentic architectures, integrating LLMs with tools and APIs, building RAG pipelines, and ensuring scalable, reliable, and cost‑efficient AI solutions. You will collaborate with cross‑functional teams to deliver real‑world AI‑driven applications.

Key Responsibilities:

• Design and implement Agentic AI systems (planner–executor, tool‑using agents, multi‑agent workflows).
• Build agents capable of reasoning, task decomposition, memory, and decision‑making.
• Integrate LLMs with tools, APIs, databases, and enterprise systems.
• Develop RAG pipelines, long‑term memory, and context management for agents.
• Orchestrate agents using frameworks like LangGraph, LangChain, CrewAI, AutoGen, LangFlow.
• Implement human‑in‑the‑loop workflows and safety guardrails.
• Optimize for latency, cost, reliability, and scalability.
• Collaborate with product, backend, and frontend teams to ship real use cases.

Required Skills:

• Strong programming experience in Python (mandatory).
• Hands‑on experience with LLMs (OpenAI, Azure OpenAI, Anthropic, Gemini, etc.)
• Experience building tool‑calling agents and workflow‑driven AI systems.
• Knowledge of RAG, embeddings, vector databases (FAISS, pgvector, Quadrant).
• API integration (REST, Webhooks, OAuth).
• Understanding of prompt engineering, agent memory, and evaluation.
• Experience with FastAPI for AI services.
• Familiarity with cloud platforms (Azure / AWS / GCP).

Good to Have:

• Experience with multi‑agent systems and agent collaboration.
• Knowledge of LLM evaluation (RAGAS, TruLens, custom metrics).
• Background in NLP, ML, or distributed systems.
• Exposure to observability (logs, traces, token usage, cost tracking).