Artificial Intelligence Engineer

Intellect Design Arena Ltd; Pune District; On-site; INR 2,500,000 - 3,500,000; Full time

Job summary

A leading software development company in Pune, India is seeking an AI Technical Architect/Engineering Lead to oversee the architecture and delivery of production-grade AI systems. The role requires a track record in delivering impactful LLM and GenAI solutions, alongside strong hands-on leadership in full-stack development. Candidates must demonstrate expertise in deploying scalable solutions on cloud platforms and articulating technical roadmaps. Join us to lead a talented team working on innovative AI projects.

Qualifications

• 2+ production LLM/GenAI solutions with real users and measurable impact.
• Experience with RAG, tool/function calling, and prompt engineering.
• Knowledge of grounding strategies and hallucination mitigation.

Responsibilities

• Lead the architecture and delivery of AI systems focusing on Generative AI.
• Design end-to-end systems for ingestion, retrieval, and orchestration.
• Deploy and scale applications on Azure/AWS using containerization.

Skills

Production LLM/GenAI solutions

RAG and tool/function calling

Prompt engineering

Agile methodologies

Tools

Python

Java

Docker

Kubernetes

JIRA

Confluence

Job description

AI Technical Architect / Engineering Lead (Generative AI & Agentic Systems)

Experience: 8–14 years overall; 2–4 years hands‑on with GenAI/LLMs

Function: Architecture + Hands‑on Engineering Leadership

About the role

You will lead the architecture, delivery, and evolution of production‑grade AI systems with a primary focus on Generative AI and agentic workflows. You’ll guide a high‑impact team across the full stack—from data and infrastructure to APIs and front‑end—ensuring performance, safety, and reliability at scale.

What you’ll do

1. Own AI architecture: Design end‑to‑end systems—ingestion, retrieval, agentic reasoning (planning, memory, tool use), guardrails, evaluation, and observability.
2. Deliver agentic workflows: Build multi‑agent, tool‑augmented systems with robust orchestration, fallback, human‑in‑the‑loop, and recovery patterns.
3. GenAI solutions: Implement RAG, structured outputs, function/tool calling; combine LLMs with deterministic microservices and domain logic.
4. Full‑stack leadership: Oversee backend services (Python/Java), APIs/middleware, and modern web front‑ends (React/Angular/Vue) for AI‑powered UX.
5. LLMOps/MLOps: Design prompt structures, chunking strategies, embeddings, freshness policies, CI/CD for prompts/models, offline/online evals, canaries, rollback, and cost/latency budgets.
6. Cloud & platform: Deploy and scale on Azure/AWS using Docker/Kubernetes; define IaC, networking, secrets, and runtime policies.
7. Security & governance: Implement defenses for prompt injection, data leakage/PII, toxicity; enforce RBAC/ABAC, auditability, compliance, performance profiling, and production SLOs/SLAs.
8. Team & stakeholders: Lead a 3–8 engineer pod; mentor developers; partner with PM/Design; translate business goals into technical roadmaps.
9. Platform stewardship: Champion and evolve our internal Purple Fabric AI platform; drive adoption and integration across products.
10. Delivery practices: Run Agile rituals; manage scope, risks, and timelines using JIRA and Confluence.

Must‑have skills

• Shipped AI systems: Track record of 2+ production LLM/GenAI solutions with real users and measurable impact.
• GenAI depth: RAG, tool/function calling, prompt engineering, structured outputs, grounding strategies, LangChain/LangGraph/LlamaIndex, and hallucination mitigation.

Seniority level

Mid‑Senior level

Employment type

Full‑time

Job function

Information Technology

Industries

Software Development