Job Summary

This role goes beyond traditional QA; the ideal candidate should be capable of validating, evaluating, and improving AI-powered systems, agents, copilots, and LLM-driven workflows while building scalable automation frameworks and intelligent quality solutions. You will work closely with Engineering, AI/ML, Platform, Product, and DevOps teams to ensure reliability, safety, observability, scalability, and quality of modern AI-native applications and Agentic systems.

Key Responsibilities

AI/LLM Quality Engineering

- Design, validate, and optimise testing strategies for AI-powered applications, copilots, chatbots, RAG pipelines, and autonomous AI agents.

- Develop AI evaluation (Evals) frameworks for:Hallucination detectionGroundednessToxicity bias validationResponse qualityContext relevancePrompt regression testingDeterminism consistencySafety and guardrail validation

- Build automated validation pipelines for LLM outputs using structured assertions, semantic scoring, embeddings, and evaluation metrics.

- Create synthetic datasets and benchmark datasets for AI testing scenarios.

- Test multi-agent orchestration workflows and agent memory/context retention.

- Validate MCP (Model Context Protocol) integrations and tool interoperability.

- Work on Context Engineering, Prompt Engineering, and Prompt Optimisation strategies.

- Evaluate latency, token usage, model cost optimisation, throughput, and scalability.

Automation Engineering

- Develop and maintain scalable UI/API automation frameworks using:Python (mandatory)Robot Framework (preferred)Playwright / Selenium / Cypress

- Automate testing for:REST APIsGraphQL APIsEvent-driven systemsStreaming systemsWebhooksMicroservicesMFE (Micro Frontend) architectures

- Build reusable automation libraries, utilities, and AI-assisted testing workflows.

- Integrate automation into CI/CD pipelines and quality gates.

AI Engineering Platform Validation

- Validate RAG architectures including:Chunking strategiesEmbedding qualityRetrieval accuracyRe-rankingVector search relevance

- Work with vector databases such as:



Pinecone Weaviate ChromaDB QdrantFAISS

- Build or validate AI agents leveraging: Lang Chain Lang Graph CrewAI Auto Gen Semantic KernelOpenAI SDKs

- Validate AI workflows involving:Tool callingFunction callingAgent memoryAgent planning/executionMulti-modal AI systemsStructured outputs

DevOps, Observability Reliability

- Build and maintain quality workflows integrated with:GitHub ActionsJenkinsGitLab CI/CDAzure DevOps

- Work with Docker and Kubernetes environments.

- Perform cloud-based testing and deployments across AWS/Azure/OCI/GCP.

- Validate distributed systems reliability and resiliency.

- Monitor AI system behaviour using observability platforms/logging/tracing tools.

- Contribute to shift-left and quality engineering best practices.

Required Skills

Must Have

- Robust programming experience in Python

- Strong understanding of Software Testing Quality Engineering principles

- Hands-on experience with:AI/LLM testingPrompt EngineeringContext EngineeringAI EvalsRAG systemsAI Agents

- Experience with:CI/CD pipelinesDocker KubernetesCloud platforms (AWS/Azure/OCI/GCP)API testing automationMicroservices testingUI automation

- Experience with SQL and data validation

- Strong debugging, analytical, and troubleshooting skills

- Experience working in Agile/Scrum environments

Preferred / Good to Have

- Experience with Robot Framework

- Experience with Playwright

- Knowledge of: Lang Chain Lang Graph Llama Index CrewAI Semantic KernelMCP (Model Context Protocol)

- Hands-on experience with:CursorGitHub CopilotClaudeGeminiOpenAI APIs

- Experience with vector databases and embeddings

- Exposure to MLOps workflows and ML lifecycle testing

- Knowledge of performance testing and security testing





- Experience validating AI governance/compliance requirements

- Experience with contract testing, chaos testing, or resilience engineering

- Familiarity with accessibility testing and cross-browser/device testing

- Exposure to synthetic monitoring and production observability

What We're Looking For

- Engineers who actively experiment with AI tools and build side projects, prototypes, PoCs, or open-source contributions.

- Strong problem solvers who can combine traditional QE practices with modern AI-native engineering approaches.

- Passion for innovation, developer productivity, automation acceleration, and intelligent testing.

- Ability to rapidly learn emerging AI frameworks, tools, and architectures.

Nice Portfolio Signals

Candidates with one or more of the following will stand out:

- GitHub repositories showcasing AI/automation projects

- AI agents or copilots built personally or professionally

- Contributions to open-source automation or AI ecosystems

- Blogs, talks, workshops, or technical content on AI/testing

- Experience integrating AI into SDLC or QE workflows

- Experience with autonomous testing systems or self-healing automation

Education

- Bachelor s/Master s degree in Computer Science, Engineering, AI/ML, or related field preferred.

- Equivalent hands-on experience and demonstrable projects are highly valued.

Bonus Skills (High Impact)

- AI Red Teaming

- LLM Security Testing (Prompt Injection, Jailbreaks, Data Leakage)

- Agent Reliability Safety Testing

- AI Cost Optimisation

- Distributed Systems Testing

- Test Data Engineering

- Feature Flag Testing

- AI Observability Telemetry

- Reinforcement Learning feedback workflows

- Human-in-the-loop evaluation systems

- Knowledge Graph integrations

- Multi-modal AI testing (vision/audio/text)

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 AI - Software Development Engineer in Test (AI - SDET) (Mumbai)
🏢 Register.com
📍 Mumbai