Job Description

About Us:

Systango Technologies Limited (NSE: SYSTANGO) is a digital engineering company that offers enterprise-class IT and product engineering services to different size organizations. At Systango, we have a culture of efficiency - we use the best-in-breed technologies to commit quality at speed and world-class support to address critical business challenges. We leverage Gen AI, AI/Machine Learning and Blockchain to unlock the next stage of digitalization for traditional businesses. Our handpicked team is adept at web & enterprise development, mobile apps, QA and DevOps. Ulster University, Sila, Cuentas, Youtility, Porsche, MGM Grand, Deloitte, Grindr, and Tawk.to are some of the top clients that have entrusted us to enhance their digital capabilities and build disruptive innovations. We believe in making the impossible, Possible and we do it literally.

Role Overview

We are seeking an

AI Engineer

to design, build, and deploy

production-grade AI systems

using

Generative AI and Large Language Models (LLMs)

. This role emphasizes

applied GenAI engineering

, including

Retrieval-Augmented Generation (RAG)

,

AI workflow orchestration

, and

multi-agent systems

, rather than deep ML theory or academic research.
You will work closely with product, platform, and engineering teams to integrate AI capabilities into real-world applications and business workflows.

Key Responsibilities

Build and maintain

AI-enabled services and applications

using Python. Design and implement

RAG pipelines

, including document ingestion, embeddings, retrieval, and response synthesis. Integrate

LLMs via APIs

(e.g., OpenAI, Azure OpenAI, Anthropic) into production systems. Develop

AI workflows

that combine retrieval, prompts, tools, agents, and post-processing. Build and manage

multi-agent systems

, defining agent roles, coordination logic, and shared context. Use

AI orchestration frameworks

such as

LangGraph, Microsoft Semantic Kernel, CrewAI

, or similar tools. Perform

LLM fine-tuning or model customization

to improve task-specific performance. Evaluate and monitor AI outputs for

quality, accuracy, latency, cost, and reliability

. Collaborate with cross-functional teams to translate business needs into scalable AI solutions.

Required Skills & Experience

Programming & Software Engineering

Strong proficiency in

Python

for AI application development. Solid understanding of

software engineering best practices

, including modular design, testing, and maintainability. Proficient with

Git and GitHub

for version control and collaboration.

Generative AI, RAG & LLMs

Hands-on experience using

LLMs via APIs

. Strong experience with

Retrieval-Augmented Generation (RAG)

, including: Embeddings creation and management Vector databases and similarity search Prompt + retrieval integration Experience with

prompt engineering

, inference, and response evaluation. Practical experience with

LLM fine-tuning or customization

(e.g., instruction tuning, domain adaptation). Understanding of

LLM limitations

, hallucinations, latency, and cost trade-offs.

AI Workflow Orchestration & Agent Systems

Experience designing

multi-step AI workflows

(sequential, branching, parallel, human-in-the-loop).
Hands-on experience with

AI orchestration and agent frameworks

such as:
LangGraph
Microsoft Semantic Kernel
CrewAI
Or equivalent tools
Ability to design and operate

multi-agent architectures

, including shared memory, tool usage, and coordination.
Understanding of

guardrails, retries, fallbacks, and failure handling

in AI pipelines.

Data, APIs & Storage

Experience building and consuming

RESTful APIs

using

FastAPI, Flask, or Django

. Comfortable working with

structured and unstructured data

(JSON, CSV, text, documents). Experience with

SQL or NoSQL databases

, including

vector databases

for RAG use cases.

Deployment & Production Readiness

Experience deploying

AI-enabled services

to production environments. Understanding of

scalability, security, observability, and monitoring

for AI systems. * Familiarity with

cloud platforms

and containerization (Docker; Kubernetes is a plus).