- AI &
- Cloud Platforms: Hands-on experience with AWS Bedrock; familiarity with LLM architectures and foundational models.

- RAG &

- Prompt Engineering: Proficiency implementing retrieval-augmented generation (RAG) systems and crafting high-quality prompts for LLM interactions.

- AI Orchestration / Agentic Workflows: Proven experience designing and implementing agentic workflows and multi-agent systems using modern orchestration frameworks (e.g., LangGraph, LlamaIndex), including tool calling, workflow routing, and structured task decomposition.

- LLMOps / Evaluation &

- Observability: Strong experience across the LLMOps lifecycle, including automated prompt/model evaluation and benchmarking (e.g., promptfoo), and production observability, tracing, and debugging

- AI Governance / Guardrails &

- Security: Demonstrated ability to implement AI guardrails and safety controls to mitigate prompt injection, prevent sensitive data leakage, enforce policy-based outputs, and ensure secure AI integrations in production environments.

- Web Technologies: Solid skills in full-stack development using modern frameworks (e.g., JavaScript/TypeScript – React, Angular, Node.js), RESTful APIs, HTML5, and CSS3.

- Backend Systems: Experience with Java, Spring Boot, Python, for building backend services.

- Cloud &

- DevOps:



Familiarity with serverless and containerized deployments (e.g., AWS Lambda, ECS/Fargate), CI/CD pipelines (GitHub Actions, Maven, Gradle, Bamboo), and infrastructure as code.

- Data &

- APIs: Comfortable integrating AI models with data sources, microservices, and external APIs;

experience with JSON, HTTP, and API authentication patterns.

- Databases: Hands-on development experience using RDBMS/SQL databases (e.g., MySQL, PostgreSQL, Oracle) and NoSQL databases (e.g., MongoDB, DynamoDB), including schema design, query optimization, and integration with web applications and AI-driven services.

- Testing &

- Quality: Experience writing automated tests (unit, integration), performance profiling, and production monitoring.

- AI-Assisted Development Tools: Hands-on experience using AI development assistants (e.g., GitHub Copilot, Amazon Q Developer, AWS Kiro, Cursor, JetBrains AI, VS Code AI extensions) to accelerate development, improve code quality, and support productivity in day-to-day engineering workflows.

- Agile / Product Delivery: Demonstrated experience delivering software in an Agile Scrum / product delivery environment, including story estimation, sprint execution, backlog refinement, collaboration with Product Owners, and continuous improvement practices.

📌 Senior Full Stack AI Engineer (Hyderabad)
🏢 Evoke Technologies
📍 Hyderabad