Gen AI Engineer

Job Description

We are looking for an enthusiastic Senior GenAI Engineer to drive our generative AI initiatives, with a strong focus on building GenAI utilities that elevate Quality Assurance practices and accelerate developer productivity across the engineering organisation.

You will design, build, and operationalise LLM-powered tools, agents, and platforms on AWS that are secure, scalable, and production-ready in a regulated environment.

Key Responsibilities

• You will be #LI-hybrid based in Hyderabad and reporting to Director Engineering
• Work as a senior GenAI engineer in an agile team to deliver high-quality, production-grade GenAI solutions within agreed timelines, aligned with business requirements and agile principles.
• Design and build GenAI-powered utilities for QA - including intelligent test case generation, test data synthesis, automated defect triage, log/anomaly summarization, and assistive code/test review tooling - to measurably improve quality and engineering velocity.
• Develop reusable GenAI accelerators, libraries, and internal copilots that increase productivity across software engineering, QA, and operations teams.
• Translate business and engineering requirements into clean, scalable Python code, applying design patterns, secure coding practices, and modern LLM application architectures (RAG, tool-use, agents).
• Build and operate LLM applications on AWS using services such as Amazon Bedrock, SageMaker, Lambda, ECS/EKS, API Gateway, S3, DynamoDB, and OpenSearch.
• Establish patterns and frameworks for prompt engineering, retrieval-augmented generation, evaluation, observability, and continuous improvement of GenAI systems.
• Champion responsible AI - guardrails, PII protection, model governance, hallucination mitigation, and compliance with security and regulatory requirements.
• Collaborate closely with cross-functional team members - QA engineers, software engineers, architects, product, and security - to design, develop, test, and release GenAI-powered software.
• Contribute to development processes and practices, fostering a culture of continuous integration, delivery, evaluation, and improvement for GenAI systems.
• Provide clear and concise documentation for prompts, models, datasets, code, processes, and system architecture to support knowledge sharing and maintainability.

Qualifications

• Bachelor's degree in engineering or a related discipline.
• 3+ years of hands-on experience in software development, with at least 1+ years working on production GenAI / LLM-based applications.
• Proven experience building secure, high-volume, mission-critical systems in regulated industries (finance / insurance / healthcare).
• Expertise in translating business requirements into clean, scalable code using design patterns and security best practices.
• Strong individual contributor and effective team collaborator, comfortable working with QA, engineering, and product stakeholders.

Technical Skills

• Strong Python development skills - building production services with frameworks such as FastAPI / Flask, Pydantic, asyncio, and modern packaging/testing tooling.
• Hands-on expertise with AWS for designing, deploying, and operating applications - Bedrock, SageMaker, Lambda, ECS/EKS, API Gateway, S3, DynamoDB, OpenSearch, IAM, CloudWatch, Step Functions.
• Strong working knowledge of GenAI fundamentals - LLMs (Claude, GPT, Llama, Mistral and similar), embeddings, tokenisation, context windows, model selection, and cost/performance trade-offs.
• Experience designing and shipping Retrieval-Augmented Generation (RAG) solutions using vector stores (OpenSearch, pgvector, Pinecone, FAISS) and hybrid retrieval patterns.
• Practical experience with prompt engineering, structured outputs, function/tool calling, and agentic patterns familiarity with frameworks such as LangChain, LlamaIndex, Bedrock Agents, or similar.
• Experience defining and running LLM evaluation frameworks - golden datasets, automated evals, regression testing, and online metrics for quality, safety, and cost.
• Building and consuming REST / gRPC APIs using microservices / SOA, with strong API design, versioning, and security practices.
• Experience writing unit and integration tests (pytest), applying TDD, and building eval harnesses for LLM-based components.
• Expertise in creating, maintaining, and reusing frameworks / libraries for GenAI utilities and shared platform capabilities.
• Experience with model fine-tuning and parameter-efficient techniques (LoRA, QLoRA), distillation, and small-language-model deployment.
• Experience with agentic frameworks, multi-agent orchestration, and emerging standards such as Model Context Protocol (MCP).
• Clean code, clean architecture, SOLID principles, and design patterns applied to data- and ML-intensive systems.
• Expertise with SQL / NoSQL databases (PostgreSQL, DynamoDB, MongoDB) for application and feature/metadata storage.
• Proficient with Docker, Kubernetes, and Git (Bitbucket, GitHub, GitLab) and CI/CD practices.
• Experience working in Agile teams (Scrum or Kanban).
• Familiar with static code analysis, dependency scanning, and vulnerability management for AI/ML applications.

Desirable Skills

• Demonstrable experience building GenAI utilities or copilots for QA and/or developer productivity (test generation, defect triage, code/test review assistants, documentation generation).
• AWS certifications - especially AWS Certified Machine Learning - Specialty, AI Practitioner, Solutions Architect, or Developer Associate.
• Experience deploying and scaling services on Amazon ECS / EKS and serverless GenAI architectures.
• Working knowledge of GenAI tools for coding (e.g., GitHub Copilot, Amazon Q Developer, Claude Code).
• Familiarity with Domain-Driven Design (DDD) and Event-Driven Architecture (EDA).
• Event streaming / messaging tools (Kafka, EventBridge, Kinesis, RabbitMQ, ActiveMQ).
• Proficient in Infrastructure as Code (IaC) using Terraform, CloudFormation, or AWS CDK.
• CI/CD tools such as GitHub Actions, GitLab CI, or Jenkins, with experience building MLOps / LLMOps pipelines.
• Experience with LLM observability and evaluation tooling (LangSmith, LangFuse, RAGAS, Helicone, Arize) and responsible-AI guardrails.

Additional Information

Our uniqueness is that we celebrate yours. Experian's culture and people are important differentiators. We take our people agenda very seriously and focus on what matters DEI, work/life balance, development, authenticity, collaboration, wellness, reward & recognition, volunteering... the list goes on.

Experian's people first approach is award-winning World's Best Workplaces™ 2024 (Fortune Global Top 25), Great Place To Work™ in 24 countries, and Glassdoor Best Places to Work 2024 to name a few. Check out Experian Life on social or our Careers Site and Glassdoor to understand why.

Experian is proud to be an Equal Opportunity and Affirmative Action employer. Innovation is a critical part of Experian's DNA and practices, and our diverse workforce drives our success. Everyone can succeed at Experian and bring their whole self to work, irrespective of their gender, ethnicity, religion, color, sexuality, physical ability or age. If you have a disability or special need that requires accommodation, please let us know at the earliest opportunity.

Benefits

Experian care for employee's work life balance, health, safety and wellbeing. In support of this endeavor, we offer best-in-class family well-being benefits, enhanced medical benefits and paid time off.

Experian Careers - Creating a better tomorrow together

This is a hybrid remote/in-office role.

Experian Careers - Creating a better tomorrow together