Infosys Recruitment 2026 – Technology Analyst, Generative AI

Infosys

Scroll down to apply

3–5 years6 days ago

Experience3–5 years

QualificationMCA, MSc, MTech, B.E., BCA, BSc or BTech

Key Responsibilities

The selected candidate will contribute to the design, development, integration and maintenance of AI-driven applications.
Design and develop AI applications using Generative AI and LLM technologies. Build application functionality that addresses business requirements and integrates appropriately with existing systems.
Build and implement Agentic AI systems that support reasoning, planning, tool usage and workflow orchestration. Ensure that workflows can be tested, monitored and maintained.
Develop RAG pipelines using vector databases and enterprise knowledge sources. Support the retrieval and use of relevant information in LLM-powered applications.
Create and maintain evaluation frameworks that measure model quality, accuracy, hallucination rates, relevance and business KPIs. Use evaluation results to improve application performance and response reliability.
Develop prompt engineering strategies and optimise LLM performance. Test different prompt structures and context strategies to improve the quality and consistency of generated responses.
Integrate AI solutions with enterprise applications, APIs, databases and cloud platforms. Ensure that application components work together reliably and meet functional requirements.
Build scalable backend services and AI workflows using Python. Develop and maintain the services required to expose AI capabilities to downstream applications.
Collaborate with business stakeholders, data scientists and solution architects to translate requirements into AI-driven solutions. Communicate technical decisions and coordinate development activities across teams.
Monitor, troubleshoot and optimise AI applications in production environments. Investigate technical issues, improve performance and support ongoing maintenance.
Stay updated with emerging AI technologies, frameworks and industry practices. Evaluate relevant developments and identify opportunities to improve application capabilities and engineering workflows.
The official description also identifies several broader technology and software engineering expectations:
Knowledge of design principles and the fundamentals of software architecture.
Understanding of performance engineering.
Knowledge of quality processes and estimation techniques.
Basic understanding of the project domain.
Ability to translate functional and non-functional requirements into system requirements.
Ability to design and code complex programmes.
Ability to write test cases and scenarios based on specifications.
Understanding of the software development lifecycle (SDLC) and Agile methodologies.
Awareness of emerging technologies and industry trends.
Logical thinking, problem-solving and collaboration skills.
These requirements indicate that the Technology Analyst role combines AI engineering with standard software development, system design, testing and delivery responsibilities.

Skills & Eligibility

Infosys is looking for candidates with professional experience in software development and the ability to work with Python-based AI applications. Applicants should have the technical foundation needed to develop AI workflows, integrate enterprise systems and support applications in production environments.
Educational qualification: MCA, MSc, MTech, Bachelor of Engineering, BCA, BSc or BTech, as listed on the official careers page.
Experience: 3–5 years, according to the official job listing.
Programming: Python programming skills.
Generative AI: Knowledge of Generative AI and large language model applications.
Retrieval-Augmented Generation: Understanding of RAG concepts and implementations.
Prompt engineering: Ability to design and refine prompts for AI applications.
AI application development: Ability to contribute to scalable AI-driven software solutions.
Problem-solving: Ability to investigate issues, evaluate results and improve application performance.
Collaboration: Ability to work with business stakeholders, data scientists and solution architects.
Important: The listed educational requirements include several undergraduate and postgraduate qualifications. Candidates should verify the degree requirements against their own background and ensure that they meet the 3–5 years of experience criterion.
Candidates with relevant professional experience in Python development, AI application engineering or related software development work should review the detailed requirements and apply if their skills match the role.
The official listing identifies the following qualifications:
Bachelor of Engineering (B.E.).
The listing does not specify a minimum CGPA or a particular graduation batch. Applicants should check the official application portal for any additional conditions.
The official listing identifies the following qualifications:
Bachelor of Engineering (B.E.).
The listing does not specify a minimum CGPA or a particular graduation batch. Applicants should check the official application portal for any additional conditions.
Python is a core technical requirement for this Technology Analyst position. It is used to develop backend services, automation workflows and AI-powered applications.
Candidates should be comfortable writing reusable Python code, working with APIs and structured data, handling errors and building maintainable application components.
Important preparation topics include:
Python data structures and programming fundamentals.
Functions, modules and reusable code.
Object-oriented programming.
Exception handling and debugging.
Working with JSON and external APIs.
Building backend services and automation scripts.
Testing and maintaining Python applications.
Generative AI and LLM technologies are central to the responsibilities described in the job listing. These systems can generate text, summarise information, assist with problem-solving and support intelligent application workflows.
Candidates should understand how LLM-powered applications are built and integrated with enterprise software. They should also be aware of limitations such as hallucinations, incomplete responses, incorrect information and the need for appropriate evaluation.
Useful topics to review include:
Large language model fundamentals.
LLM application architecture.
Prompt construction and response handling.
Integrating LLMs through APIs.
Context management and response quality.
Testing and evaluating AI-generated outputs.
Monitoring reliability and application performance.
RAG combines information retrieval with generative AI. Instead of relying only on information learned during model training, a RAG system retrieves relevant information from a configured knowledge source and provides it as context to the language model.
The Infosys job description specifically mentions building RAG pipelines using vector databases and enterprise knowledge sources.
Candidates should understand the main stages of a RAG pipeline:
Data ingestion: Collecting and preparing documents or information sources.
Chunking: Dividing documents into suitable sections for retrieval.
Embeddings: Representing content as numerical vectors for semantic comparison.
Vector storage: Storing embeddings and related metadata in a retrieval system.
Retrieval: Finding relevant content based on a user’s query.
Generation: Supplying retrieved information to an LLM to produce a response.
Evaluation: Assessing whether retrieved content and generated answers are relevant, accurate and grounded.
Candidates should be ready to explain how they would improve retrieval quality, reduce irrelevant context and evaluate the usefulness of generated responses.
The job description includes building Agentic AI systems capable of autonomous reasoning, planning, tool usage and workflow orchestration.
Agentic AI applications can use language models to select actions, call external tools and coordinate multiple steps toward a defined objective. These systems require suitable boundaries, error handling, evaluation and monitoring.
Useful topics include:
AI agents and tool calling.
Task planning and multi-step workflows.
Integrating APIs and external tools.
Workflow orchestration.
Handling failures and unexpected outputs.
Observability and monitoring of agent behaviour.
Human oversight and safeguards for consequential actions.
The role description emphasises practical system development rather than research alone. Candidates should understand how agent workflows connect with APIs, enterprise data and application services.
Prompt engineering involves designing instructions and context that help an LLM produce useful, relevant and consistent responses.
The job listing identifies prompt engineering as a technical requirement. Candidates should understand how prompt structure, context selection, formatting instructions and examples can influence model outputs.
Preparation topics include:
Writing clear and specific instructions.
Structuring context and task requirements.
Using examples to guide output formats.
Managing long or complex prompts.
Testing prompts against representative scenarios.
Evaluating quality and consistency.
Reducing ambiguity and unsupported responses.
Strong prompt engineering should be supported by systematic evaluation rather than relying solely on subjective judgement of a few example outputs.
The responsibilities include creating and maintaining AI evaluation frameworks to measure model quality, accuracy, hallucination rates, relevance and business KPIs.
This means candidates should understand why evaluating an LLM application requires more than checking whether a response sounds convincing.
Useful evaluation concepts include:
Accuracy and relevance of generated responses.
Grounding against source documents.
Detection of unsupported statements or hallucinations.
Retrieval quality and relevance of supporting context.
Consistency across representative test cases.
Latency, cost and operational performance.
Business-specific performance measures.
Candidates should be able to describe how an evaluation dataset is prepared, how results are measured and how evaluation outcomes guide improvements to a prompt, retrieval process or application workflow.
The RAG requirements mention vector databases and enterprise knowledge sources. These components help an application retrieve information that is relevant to a user query.
Candidates should understand the purpose of embeddings, vector similarity, metadata filtering and document retrieval. They should also understand how enterprise data can be prepared and connected to an AI application while respecting access controls and data-handling requirements.
The supplied job description does not name a mandatory vector database product. Applicants should therefore focus on the underlying concepts and any systems they have used in their projects.
Infosys expects candidates to integrate AI solutions with enterprise applications, APIs, databases and cloud platforms. This requires understanding how software components communicate and how an AI service fits into a broader application environment.
Useful areas to review include:
REST APIs and JSON.
Authentication and access controls.
Backend service design.
Database connectivity.
Integrating AI services with business applications.
Error handling and retries.
Deployment, monitoring and production support.
The job description includes monitoring, troubleshooting and optimising AI applications in production environments.
Production AI systems must operate reliably after deployment. Engineers need to investigate failures, monitor performance, understand the causes of poor-quality responses and implement improvements without disrupting dependent systems.
Candidates should prepare examples of debugging applications, improving API performance, monitoring services or resolving problems in deployed software.
The official listing includes MCA, MSc, MTech, Bachelor of Engineering, BCA, BSc and BTech.
The technical and professional requirements list Python, Retrieval-Augmented Generation (RAG) and prompt engineering. Candidates should also review the detailed responsibilities, which include Agentic AI, LLM applications, enterprise integrations and production monitoring.
October 20, 2026

Note: This job is posted on external sites. Joblit shares the listing for convenience and does not take responsibility for third-party content.

Apply Now

Suggested Jobs

Infosys Recruitment 2026 – Technology Analyst, Generative AI

Key Responsibilities

Skills & Eligibility

Suggested Jobs

American Express Recruitment 2026 – Apprentice Enterprise Technology Services

Eaton Recruitment 2026 – Market Research Analyst

Diligent Recruitment 2026 – Junior Research Analyst

CGI Recruitment 2026 – System Engineer – Data Analyst

Salesforce Recruitment 2026 – APAC Payroll Analyst

3M Recruitment 2026 – Quality Testing Associate Analyst

Genpact Recruitment 2026 – Business Analyst