Generative AI Engineer

Job Title: TP2 Developer – Generative AI

Experience: 5 Years (1–2 Years in Generative AI)

Employment Type: Full-Time

Job Summary:

We are seeking a TP2 Developer – Generative AI with strong backend engineering experience and hands-on exposure to Generative AI technologies. The ideal candidate will contribute to the development of AI-powered applications using Large Language Models (LLMs), support prompt engineering and RAG-based pipelines, and help integrate GenAI solutions into enterprise workflows. This role requires close collaboration with senior engineers and AI architects while continuously learning and applying emerging GenAI concepts.

Key Responsibilities:

The candidate will contribute to the design, development, and enhancement of Generative AI–powered applications using LLMs and related technologies. They will assist in integrating GenAI models into real-world business workflows and backend systems.

The role involves supporting prompt engineering activities and building Retrieval-Augmented Generation (RAG) pipelines using tools such as LangChain or equivalent frameworks. The candidate will help implement prompt chaining, retrieval workflows, and context management under guidance from senior team members.

The candidate will work on integrating and maintaining vector databases to enable semantic search and knowledge retrieval. This includes managing embeddings, indexing strategies, and query workflows using vector store technologies.

They will collaborate on developing AI-driven workflows and agents that support multi-step reasoning, task automation, and orchestration of LLM-based processes.

The role requires developing and maintaining backend services and APIs using Python within a microservices-based architecture. The candidate will work on system integrations, data flows, and service-to-service communication.

The candidate will participate in CI/CD pipelines and deployment processes, leveraging DevOps tools such as Docker, GitHub Actions, Jenkins, or similar technologies.

They will work with database systems, including SQL and NoSQL databases such as PostgreSQL, to support backend services and GenAI pipelines.

The candidate is expected to collaborate closely with cross-functional teams, learn from senior engineers and AI architects, and actively contribute to technical discussions and continuous improvement initiatives.

Required Qualifications:

The candidate must have a total of 5 years of professional software development experience, with at least 1 to 2 years of hands-on experience working on Generative AI or LLM-based projects.

Strong programming skills in Python are required, with a minimum of 3 years of experience.

The candidate should have hands-on exposure to Generative AI tools and frameworks such as OpenAI APIs, Hugging Face Transformers, or similar platforms.

Experience or exposure to LangChain or equivalent GenAI workflow orchestration tools for prompt engineering and RAG pipelines is required.

The candidate should have experience working with vector databases such as Chroma, Pinecone, Weaviate, or similar technologies.

A minimum of 3 years of experience in developing backend services, REST APIs, and microservices-based systems is required.

The candidate should have experience working with database systems, including both SQL and NoSQL databases, for 3 to 5 years.

Hands-on experience with DevOps tools such as Docker and CI/CD pipelines is required, along with exposure to at least one cloud platform such as AWS, GCP, or Azure.

Preferred Skills:

Experience working with AI agents, semantic search, or LLM-based workflow automation is an advantage.

Familiarity with scalable system design, cloud-native architectures, and secure API development is a plus.

A strong learning mindset, good communication skills, and the ability to work effectively in a collaborative team environment are essential.