Engineering Manager

Questhiring; Gurugram District; On-site; INR 4,500,000 - 7,000,000; Full time

Job summary

Questhiring seeks an Engineering Manager - AI / Agentic AI to lead design, development, and deployment of AI-powered products and intelligent agent systems. You will guide a team combining AI/ML engineers and software engineers to build production-grade Agentic AI solutions capable of reasoning, planning, tool usage, and autonomous workflows.

The role requires hands-on GenAI expertise, architecture leadership, and a track record of delivering AI at scale.

Qualifications

• 10-14 years of software/engineering experience.
• Strong hands-on experience building Generative AI / LLM applications.
• Expertise in RAG architecture and implementation.
• Hands-on with LangChain and/or LangGraph.
• Understanding of Agentic AI architectures and AI Agents.
• Experience with LLM orchestration, prompt engineering, tool calling, agent memory and workflows.
• Proficiency in Python and cloud-native architectures.
• Experience with vector databases and embedding models.
• Track record of taking AI solutions from PoC to production.
• Familiarity with AI evaluation, observability, and production monitoring.
• Experience with AWS, GCP, or Azure.
• Knowledge of Docker, Kubernetes, CI/CD.

Responsibilities

• Lead and mentor AI/ML engineers and software engineers.
• Define technical roadmap and architecture for GenAI and Agentic AI platforms.
• Drive engineering best practices across design, development, testing, deployment, monitoring, and improvement.
• Translate business problems into scalable AI-powered solutions.
• Build an engineering culture focused on innovation, quality, reliability and speed.
• Architect and build AI Agents and multi-agent systems with reasoning, planning and tool usage.
• Design agent workflows using LangChain, LangGraph, AutoGen, CrewAI or equivalents.
• Work with OpenAI, Anthropic, Google, Meta or open-source LLMs.
• Design and optimize RAG pipelines for accuracy, latency and cost.
• Establish LLMOps / MLOps practices and robust CI/CD for AI apps.
• Ensure AI observability covering latency, cost, hallucination, and performance.

Skills

GenAI & LLM apps

RAG architecture

LangChain/LangGraph

AI Agents & multi-agent systems

Prompt engineering

Tool calling & agent memory

Python

REST APIs & microservices

Cloud platforms (AWS/GCP/Azure)

Docker & Kubernetes

CI/CD & automated testing

Vector databases & embeddings

LLMOps / MLOps

Tools

LangChain

LangGraph

AutoGen

CrewAI

Semantic Kernel

Pinecone

Weaviate

Milvus

FAISS

Elasticsearch/OpenSearch

pgvector

Job description

We are looking for an experienced Engineering Manager - AI / Agentic AI to lead the design, development, and deployment of next-generation AI-powered products and intelligent agent systems.

The ideal candidate will combine strong engineering leadership with hands-on expertise in Generative AI, LLMs, RAG, LangChain, LangGraph, AI Agents, and scalable AI architectures.

You will lead a team of engineers and AI specialists to build production-grade Agentic AI solutions that can reason, plan, use tools, interact with enterprise systems, and autonomously execute complex workflows.

This is a highly impactful role for someone who has moved beyond experimentation and has experience taking GenAI/Agentic AI solutions from PoC to production at scale.

Key Responsibilities

Engineering & AI Leadership

• Lead and mentor a team of AI/ML Engineers, Software Engineers, and AI specialists.
• Define the technical roadmap and architecture for GenAI and Agentic AI platforms.
• Drive engineering best practices across design, development, testing, deployment, monitoring, and continuous improvement.
• Translate business problems into scalable AI-powered solutions.
• Build a strong engineering culture focused on innovation, quality, reliability, and speed.

Agentic AI & LLM Engineering

• Architect and build AI Agents and multi-agent systems capable of reasoning, planning, decision-making, tool usage, and task execution.
• Design agent workflows using frameworks such as LangChain, LangGraph, AutoGen, CrewAI or equivalent frameworks.
• Build systems involving function/tool calling, agent memory, planning, orchestration, routing, and autonomous workflows.
• Evaluate and select appropriate LLMs and AI models based on use case, latency, cost, accuracy, and scalability.
• Work with models from OpenAI, Anthropic, Google, Meta, open-source LLMs, or equivalent platforms.

RAG & Knowledge Systems

• Design and implement production-grade Retrieval-Augmented Generation (RAG) architectures.
• Work with vector databases, embeddings, semantic search, hybrid search, reranking, chunking, indexing, and retrieval strategies.
• Build enterprise knowledge systems that combine structured and unstructured data.
• Optimize RAG pipelines for accuracy, relevance, latency, scalability, and cost.
• Experience with technologies such as Pinecone, Weaviate, Milvus, FAISS, Elasticsearch/OpenSearch, pgvector or equivalent.

AI Platform & Production Engineering

• Drive the development of scalable APIs, services, and infrastructure supporting AI applications.
• Build production-grade AI systems with strong focus on availability, observability, security, scalability, and performance.
• Establish LLMOps / MLOps practices for model deployment, monitoring, evaluation, and lifecycle management.
• Implement AI observability and monitoring covering latency, token consumption, cost, hallucination, quality, and model performance.
• Establish robust CI/CD and automated testing for AI applications.

AI Evaluation & Quality

• Define frameworks for evaluating LLM and Agentic AI applications.
• Establish evaluation strategies for accuracy, groundedness, relevance, hallucination, toxicity, safety, and task completion.
• Experience with AI evaluation frameworks/tools such as DeepEval, RAGAS, LangSmith, Arize Phoenix or equivalent.
• Build feedback loops and continuously improve AI systems based on production performance.

Stakeholder & Product Collaboration

• Partner closely with Product, Data Science, Architecture, and Business teams to identify high-value AI opportunities.
• Translate product requirements into technical architecture and execution plans.
• Communicate complex AI concepts effectively to senior leadership and non-technical stakeholders.

Must-Have Skills

• 10-14 years of overall software/engineering experience.
• Strong hands-on experience building Generative AI / LLM applications.
• Strong expertise in RAG architecture and implementation.
• Hands-on experience with LangChain and/or LangGraph.
• Strong understanding of Agentic AI architectures and AI Agents.
• Experience with LLM orchestration, prompt engineering, tool/function calling, agent memory and workflows.
• Strong programming skills in Python.
• Strong experience with REST APIs, microservices, distributed systems, and cloud-native architectures.
• Experience working with vector databases and embedding models.
• Experience taking AI solutions from PoC to production.
• Strong understanding of LLM evaluation, observability, and production monitoring.
• Experience with cloud platforms such as AWS, GCP, or Azure.
• Strong understanding of Docker, Kubernetes, CI/CD, and scalable cloud infrastructure.

Good to Have

• Experience building multi-agent systems.
• Experience with LangGraph, AutoGen, CrewAI, Semantic Kernel or similar frameworks.
• Experience with MCP (Model Context Protocol) and tool-based AI architectures.
• Experience with DeepEval, RAGAS, LangSmith, Arize Phoenix or equivalent evaluation/observability tools.
• Experience with fine-tuning, LoRA/PEFT, model optimization, or open-source LLMs.
• Knowledge of transformers, Hugging Face, PyTorch or TensorFlow.
• Experience with AI security, guardrails, prompt injection prevention, data privacy, and responsible AI.
• Experience building AI applications involving real-time decisioning or high-volume enterprise workflows.
• Experience with event-driven architectures and streaming platforms such as Kafka.
• Exposure to GenAI product development and AI-first engineering organizations.

What We Are Looking For

The ideal candidate is someone who:

• Has strong engineering fundamentals along with deep GenAI expertise.
• Has actually built and deployed Agentic AI systems, rather than only working on AI PoCs.
• Understands how to design reliable, scalable and cost-efficient LLM applications.
• Can balance hands-on technical contribution with engineering leadership.
• Has experience managing and mentoring strong engineering teams.
• Is passionate about the rapidly evolving Agentic AI ecosystem and actively experiments with emerging frameworks, models, and architectures.