Agentic AI Engineer (Fractional)

Getsubstance.co Pte. Ltd.; India; On-site; INR 1,200,000 - 2,400,000; Full time

Job summary

Substance is seeking an Agentic AI Engineer to design, deploy, and maintain production-grade AI agents that automate real business workflows. You will build multi-agent systems, integrate them with internal tools, and optimize for token efficiency, latency, and accuracy.

The role focuses on real-world deployments, with emphasis on observability, failure handling, and collaboration with business stakeholders to translate processes into agent workflows.

Qualifications

• Minimum 2 production-deployed agentic systems experience.
• Proficiency in Python and LangChain/LangGraph or equivalent.
• Experience with tool-calling, RAG pipelines, memory management, and multi-agent coordination.
• Familiarity with MCP servers and API integrations.
• Cost-aware engineering mindset—justify model choice by task requirements.

Responsibilities

• Design and build multi-agent systems that automate business processes.
• Integrate agents with internal tools (CRM, ERP, databases, APIs).
• Optimize agent performance for cost per task (tokens, latency, accuracy).
• Set up observability and monitoring for production agents.
• Translate business pain points into agent workflows and iterate deployed agents.

Skills

Python

LangChain/LangGraph

Multi-agent systems

APIs integration

Cost-aware engineering

Tools

MCP servers

Memory management

Tool-calling

RAG pipelines

Job description

Our client is looking for Agentic AI Engineer to build and deploy AI agents that automate real business workflows — reducing operational cost, headcount dependency, and turnaround time. This is a hands‑on implementation role, not R&D. If your experience lives in notebooks, courses, and demos, this role is not for you.

What You'll Own

• Design and build multi-agent systems that replace or augment manual business processes
• Integrate agents with internal tools (CRM, ERP, databases, APIs, communication platforms)
• Optimize agent performance for cost per task — token efficiency, latency, and accuracy
• Set up observability and monitoring so agents don't fail silently in production
• Work directly with business stakeholders to translate process pain points into agent workflows
• Maintain and iterate on deployed agents — not a build-and-forget role

Requirements

• Minimum 2 production-deployed agentic systems — not POCs, not demos, not coursework. Real systems, real users, real business impact. You must be able to speak to what broke, how you fixed it, and what it saved
• Proficiency in Python, LangChain/LangGraph or equivalent orchestration frameworks
• Experience with tool-calling, RAG pipelines, memory management, and multi-agent coordination
• Familiarity with MCP servers and API integrations
• Cost-aware engineering mindset — can justify model choice (when to use GPT-4o vs Haiku vs Sonnet) based on task requirements, not preference
• Understanding of guardrails, human-in-the-loop design, and failure handling

How We Evaluate You — Interview Process

Theory will not get you through. Expect:

• Production walkthrough — show us a live or previously deployed agent. Walk us through the architecture, what failed, and how you resolved it
• Cost breakdown — explain the token/compute cost of a system you built and how you optimized it
• Live build task — given a business process, design an agent workflow on the spot

What Good Looks Like

• Agents running in production, not in slides
• Builds lean — chooses the cheapest model that does the job reliably, not the most impressive one

What Will Get You Rejected

• Portfolio of tutorials and Jupyter notebooks with no deployment history
• Can explain LangChain architecture but never shipped one to production
• Optimizes for technical elegance over business outcome

What You Won't Be Doing

• Academic research or model training
• Waiting for perfect requirements — expected to drive clarity from ambiguous briefs
• Building without a business case

At Substance, we’re all about action, not just talk. If your profile aligns with what we need, you’ll hear from us within 1-2 weeks. If not, no fluff—just know we value your interest and will keep you in mind for future roles where your skills can make an impact. We focus on real connections and meaningful matches, so when the right opportunity comes, we’ll be ready to make it happen.

01 Interview +

01 Interview

We’ll start by sending you an interview with some preliminary questions to get things rolling. From there, we’ll dive deeper with a screening call to verify your profile, share the details of the opportunity, and introduce you to the client’s profile. This is your time to shine, as we’ll be representing you to our clients. And don’t worry—we’ll make sure you’re fully prepared before those conversations. We value your time, so expect to hear back from us within 1-2 weeks.

02 Assessment +

02 Assessment

The hard part is over! Depending on the position, there may be a task or project to help us better understand your skills in action. This isn’t just about what’s on paper—it’s a chance for you to shine andshow us what you can bring to the table.

03 Feedback +

03 Feedback

We believe in open, two-way communication. After the assessment, we'll provide detailed feedback so you know exactly where you stand, and we’ll also ask for your input on the process—your perspective truly matters to us. No matter the outcome, you’ll hear from us, allowing everyone to learn and refine their interview skills. And remember, the door isn't closed forever; sometimes, clients need a bit more time to decide. You can expect to hear back from us within a week or less, and we'll keep everything clear and straightforward along the way.

04 Decision +

04 Decision

If everything falls into place, we’ll walk you through the offer and what it means to join our client or even our team. And if it’s not the right fit this time, no worries—we’ll keep you in mind for future roles that might be an even better match.

We don’t have 5,000 jobs. Just the right ones.

We work with a small number of companies on roles that are approved, funded, and actively hiring. If it’s here, it’s real — and it’s being worked properly.

We don't list everything, just roles worth taking seriously.

We won’t promise outcomes. We will promise how we work.

You’ll get honest feedback when we have it, clarity on where you stand andno padding pipelines or forcing fits.

If we put you forward, it’s intentional.

No farming. No ghosting.

If there isn’t a role for you today, you can still stay visible.

Being in our network means we reach out when a role actually matches,your profile is reviewed by a recruiter, not software andyou’re not marketed blindly.

It’s a holding place for future conversations.