Generative AI Engineer

Role: Generative AI Engineer

Exp: 7+ Year

Location:Pune

Must Have Technical/Functional Skills

Experience in Python (FastAPI).

Experience in FAISS ,Vector DB

Proficiency in JavaScript for backend and lightweight frontend support (excluding React JS).

Strong grasp of RESTful APIs integration and WebSocket communication.

Expertise in Large Language Models (LLMs) usage, including fine and dynamic prompt engineering for

Generative AI applications.

Hands-on experience with LangGraph Langchain agents for building and orchestrating AI workflows.

Experience with Redis (cache, streams, pub/sub patterns) for real-time chat handling.

Experience with OAuth2.0 / JWT based API security.

Good understanding of event-driven architectures and asynchronous programming (async/await).

Experience working with relational or NoSQL databases (Teradata, MongoDB, SOLR, etc.).

Ability to optimize system performance (scalability, fault tolerance).

Familiarity with containerized application deployment on OpenShift, including CI/CD pipelines and automation tools.

Roles & Responsibilities

Owns end to end solution design Collaborate and work closely with the customer Cisco leader daily basis for review

Performance optimization

Customer-facing technical leadership to effectively communicate design decisions, challenges, trade-offs, and limitations

Design and build scalable APIs using FastAPI.
Extensibility, maintainability, scalability, and overall future-readiness assessment

Utilize Large Language Models (LLMs) and SLM for Generative AI-based application development, applying fine and

dynamic prompting techniques to optimize AI responses.

Develop and maintain LangGraph Langchain agents to orchestrate complex AI workflows and agentic automation.

Implement robust asynchronous event handling and improve system resilience with retries,

backoff, and failure recovery patterns.

Review and leads developers code for best practices and efficiency day to day

Set up error handling, monitoring, and logging standards, including observability for LLMs and AI workflows.

Implement OAuth2.0 and JWT validation security mechanisms.

Deploy and manage code on OpenShift containers, ensuring containerized application scalability and reliability.