AI Systems Engineer (Backend + GenAI Infrastructure)

Predictive Data Sciences; Hyderabad, Chennai, Bengaluru; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

Predictive Data Sciences invites a Systems Engineer with a passion for AI to design scalable cloud infrastructure and state management for autonomous agents. You will architect asynchronous runtimes enabling planning, coding, and reliable execution at scale.

The role emphasizes cloud architecture, backend services, and ML ops, including RAG pipelines and prompt management, with a focus on production-grade reliability and performance.

Qualifications

• Strong proficiency in Python (FastAPI/Django) and database schema design (PostgreSQL, NoSQL).
• Experience with cloud platforms (GCP Vertex, AWS, Vercel) and containerization (Docker/Kubernetes).
• Experience integrating LLMs/SLMs via APIs and orchestrating workflows (LangChain, LlamaIndex).

Responsibilities

• Design and implement scalable backend services with robust APIs using FastAPI.
• Architect asynchronous agent orchestration between frontend interfaces and backend agents.
• Deploy cloud infrastructure on AWS/GCP/Vercel with secure authentication and rate limiting.
• Build Knowledge Studio backend APIs and storage schemas for prompts and domain concepts.
• Manage ML ops tasks: deploying SLMs, RAG pipelines, fine-tuning and evaluations.
• Integrate LLMs/SLMs via APIs and orchestrate workflows with LangChain/LlamaIndex.

Skills

System Design

Python

Async Patterns

Cloud Native

AI Integration

Frontend integration

Tools

FastAPI

Django

PostgreSQL

NoSQL

Docker

Kubernetes

LangChain

LlamaIndex

Celery

Redis

React/Next.js

Job description

We are looking for a strong Systems Engineer with a passion for AI to build the backbone of our agentic platform. You wont just be identifying insights or prompting modelsyou will be architecting the cloud infrastructure, state management systems, and asynchronous runtimes that allow complex AI agents to plan, code, and execute reliability at scale.

This is a high-impact role for a builder who understands that a great AI agent is only as good as the system architecture running it.

What Youll Work On

Core Systems & Cloud Architecture (70%)

Build Scalable Backend Services: Design and implement robust APIs (FastAPI) that handle multi-turn conversations, manage complex state, and persist execution artifacts (plans, code, logs) to a permanent database layer.

Asynchronous Agent Orchestration: Architect the communication layer between front-end interfaces and backend agents, implementing async patterns (WebSockets, SSE, Queues) to handle long-running tasks.

Cloud & Security: Deploy secure, horizontally scalable infrastructure on platforms like Vercel, Google Vertex AI, or AWS. Handle authentication, rate limiting, and secure execution sandboxes.

Knowledge Management Support: Build the "Knowledge Studio" backendAPIs and storage schemas that allow users to manage prompts, documentation, and domain concepts dynamically.

AI Engineering & ML Ops (30%)

Model Orchestration: Deploy and manage Small Language Models (SLMs) on the cloud for specialized implementation subtasks (e.g., ambiguity resolution), optimizing for latency and cost.

RAG & Context Engineering: Implement retrieval pipelines that dynamically fetch the right context for the agent, ensuring high relevance and low hallucination.

Fine-tuning & Evaluation: Manage pipelines for fine-tuning models on specific domains (coding, tool selection) and running automated evaluations of agent performance.

Technical Skills

System Design: Strong proficiency in Python (FastAPI/Django) and experience designing schema for complex applications (PostgreSQL, NoSQL).

Cloud Native: Experience deploying and scaling on modern cloud platforms (GCP Vertex, AWS, Vercel) and using containerization (Docker/Kubernetes).

AI Integration: Practical experience integrating LLMs/SLMs via APIs and orchestrating workflows (LangChain, LlamaIndex, or custom orchestration).

Async Patterns: Understanding of how to handle long-running jobs (Celery, Redis, Queues) and real-time frontend updates.

Soft Skills & Mindset

Engineering First: You treat AI agents as software systems that need to be tested, debugged, and versioned.

Versatility: You are comfortable jumping from optimizing a SQL query to finetuning a Llama-3 model.

Problem Structuring: You can take a high-level goal like "handle ambiguity" and break it down into a technical workflow involving specific model calls and UI interaction states.

Bonus Points For

• Experience with Vector Databases (Pinecone, Weaver, pgvector) at scale.
• Experience building Agentic Workflows (planning, tool use, reflection loops).
• Familiarity with finetuning techniques (LoRA, PEFT) for SLMs.
• Background in frontend integration (React/Next.js) to understand the full user lifecycle.

Who Will Thrive in This Role

Youll be a great fit if you:

Are a software engineer first who loves AI, rather than a data scientist trying to learn engineering.

Want to build the engine, not just the fuel.

Enjoy the challenge of making nondeterministic LLMs behave reliably in a production system.