Job Description

We are seeking a highly skilled and hands-on Generative AI Engineer with a strong background in Retrieval-Augmented Generation (RAG). The ideal candidate will bring over 7 years of experience in software engineering or machine learning, including 2 3 years of focused expertise in Generative AI. This role demands deep technical fluency in Google Agent Space, Google Cloud Platform (GCP), Vertex AI, and Python, as well as practical experience in LLM model selection, MCP integration, and RAG pipeline implementation. A solid grasp of chunking strategies for optimizing LLM performance is essential.

You will play a pivotal role in designing and deploying cutting-edge AI-powered solutions that drive innovation and deliver measurable business value.

Key Responsibilities

- Design and implement RAG pipelines that integrate external knowledge sources (e.g., vector databases, search engines) with generative models.
- Develop and optimize retrieval components, including dense and sparse retrievers using tools like FAISS, Elasticsearch, or Vespa.
- Fine-tune and evaluate LLMs (e.g., GPT, LLaMA, Mistral) for improved performance in retrieval-augmented tasks.
- Build scalable APIs and services to expose RAG capabilities to downstream applications.
- Conduct rigorous evaluation of retrieval and generation quality using metrics like MRR, BLEU, ROUGE, and human-in-the-loop feedback.
- Collaborate with ML engineers and data scientists to align model outputs with business goals and user needs.
- Implement caching, ranking, and filtering strategies to improve relevance and latency in real-time systems.
- Stay current with research in retrieval-augmented generation, semantic search, and hybrid architectures.

Qualifications





- 7+ years of total experience in software development or AI engineering.
- 2 3 years of hands-on experience in Generative AI and LLMs.
- Proficiency in:
- Python Fast API for AI development and integration.
- Google Cloud Platform (GCP) and Vertex AI.
- Google Agent Space for conversational AI solutions.

- Experience with:

- RAG implementation and chunking strategies.
- LLM model selection, prompt engineering, and MCP integration.

- Strong understanding of AI/ML lifecycle and deployment best practices.
- Educational background: 10 + 2 + 4 (Bachelor s degree in Computer Science, Engineering, or related field).

Key Competencies

- Deep understanding of NLP and IR: Familiarity with transformer architectures, semantic search, and vector embeddings.
- Experience with LLMs: Hands-on with Hugging Face Transformers, LangChain, OpenAI APIs, or similar frameworks.
- Knowledge of retrieval systems: Proficiency in FAISS, Elasticsearch, Pinecone, Weaviate, or similar.
- Model evaluation skills: Ability to design experiments and interpret results to improve system performance.
- Solid programming skills: Python is a must; experience with RESTful APIs, Docker, and cloud platforms (AWS/GCP/Azure) is a plus.
- Familiarity with RAG architecture: Understanding of how retrieval and generation components interact and can be optimized jointly.
- Team collaboration: Comfortable working in cross-functional teams and communicating technical concepts clearly.
- Bias mitigation and safety awareness: Knowledge of ethical AI practices and how to reduce hallucinations and misinformation in generative systems.

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 Engineer Advisor (Hubballi)
🏢 SSD Shared Services
📍 Hubballi