BENGALURU · FULLTIME
AI Test Engineer - Test Lead
Fidelity International
Bengaluru · onsite · Posted 2d ago
Sourced from
Undisclosed3–6 yrsfulltimeBengaluru
Your match
?
Sign in to see your match score, skill gaps & tailored resume.
Section · 01
About this role
Job Summary
Were proud to have been helping our clients build better financial futures for over 50 years. How have we achieved thisBy working together - and supporting each other - all over the world. So, join our Asset Managemrtn Platform (AMP) team and feel like youre part of something bigger.
Job Details Title AI Test Engineer (Test Lead)
Department ISS delivery - development - gurgaon
Location INB905E
Level 4
About your team The Investment Solutions Services (ISS) delivery team provides team provides systems development, implementation and support services for FILs global Investment Management businesses across asset management lifecyle. We support Fund Managers, Research Analysts, Traders and Investment Services Operations in all of FILs international locations, including London, Hong Kong, and Tokyo
About your role You will join the QE team as an AI Test Engineer (Test Lead) and play a key role in assuring the quality, reliability, and trustworthiness of AI-powered applications across IM Technology. In addition to traditional software testing, you will be responsible for validating Generative AI solutions, Retrieval Augmented Generation (RAG) systems, AI agents, and Large Language Model (LLM) based applications deployed within the organisation.
Your responsibilities will include:
- Validate LLM-based applications for accuracy, consistency, robustness, and reliability across a wide range of business scenarios.
- Test RAG (Retrieval Augmented Generation) systems by evaluating retrieval quality, context relevance, grounding, answer correctness, and response completeness.
- Evaluate AI Agents and Agentic workflows including tool usage, planning, reasoning, task completion, decision-making, and failure recovery scenarios.
- Design and execute evaluation frameworks for GenAI applications using industry-standard tools such as DeepEval, RAGAS, LangSmith, Phoenix, or similar evaluation platforms.
- Assess AI systems for hallucinations, factual correctness, context adherence, citation quality, and response relevance.
- Test conversational AI systems for multi-turn interactions, context retention, memory handling, and user experience consistency.
- Validate AI guardrails, prompt templates, safety controls, content filtering mechanisms, and responsible AI requirements.
- Perform adversarial, negative, and edge-case testing to identify vulnerabilities such as prompt injection, jailbreak attempts, data leakage, and unsafe outputs.
- Create and maintain benchmark datasets, golden test sets, synthetic test data, and evaluation pipelines for continuous AI quality assessment.
- Validate model performance across different prompts, model versions, configurations, and environments.
- Understand business requirements, user stories, and AI use cases to define effective test strategies and quality gates.
- Collaborate with Product Owners, Business Analysts, AI Engineers, and Developers to validate AI-enabled features and solutions.
- Develop and maintain automation frameworks and test suites using Python and modern open-source testing tools.
- Design and execute functional, integration, regression, and end-to-end tests across traditional and AI-powered applications.
- Good understanding of Large Language Models (LLMs), Generative AI concepts, prompt engineering, embeddings, vector databases, and RAG architectures.
- Hands-on experience testing AI/GenAI applications in production or pre-production environments.
- Experience with AI evaluation frameworks such as DeepEval, RAGAS, LangSmith, Phoenix, Promptfoo, TruLens, or similar tools.
- Understanding of AI quality metrics including faithfulness, answer relevancy, context precision, context recall, hallucination detection, and toxicity assessment.
- Experience testing AI Agents and agentic frameworks such as LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar platforms.
- Familiarity with vector databases such as Pinecone, Weaviate, Chroma, OpenSearch, Azure AI Search, or similar technologies.
- Knowledge of AI observability and monitoring concepts.
- Understanding of AI security risks including prompt injection, jailbreaks, data leakage, and model misuse scenarios.
- Experience building automated AI evaluation pipelines integrated with CI/CD processes.
- Exposure to cloud AI services such as Azure OpenAI, AWS Bedrock, Google Vertex AI, or OpenAI APIs would be advantageous.
Sourced from naukri
Let the agent run this one for you.
Tailored resume, auto-apply, and referral lookup — in under 2 minutes.
Section · 02
Skills
AutomationBedrockFuturesAI evaluationCrewaiAzure Aiapiscloud aiAsset Managementaws bedrockamazon web servicesBusiness RequirementsimAzure OpenAIEmbeddingsai securityConversational AicloudMicrosoft AzureGenerative AiArtificial Intelligence
Section · Company
About Fidelity International
Fidelity International
Financial Services
4.5k+
employees
1969
57 years old
New Delhi, Delhi
India
About
Fidelity International operates as a major investment services provider, delivering diverse financial solutions and expertise across global markets.
Industries
Financial ServicesConsulting
Employee ratings
772 reviews
3.6/ 5
Culture
3.5
Career growth
3.0
Work-life
3.7
Employees rate it well for
Work Life Balance124Work Culture85Senior Management81Salary55Office Politics53
Find them on