Hiring For Generative AI Expert For Trivandrum Location

Total exp : 6 years

Relevant :3 years

skills: RAG, LLM, Vector db, GenAI

Job Location : Trivandrum

Key Responsibilities:

• Design, build, and optimize RAG pipelines for document-level and multi-turn QA

systems.

• Fine-tune or prompt-tune foundation models (LLMs) for domain-specific tasks.
• Develop and deploy ML/DL models to support NLP/NLU tasks like

summarization, classification, and retrieval scoring.

• Integrate vector databases, semantic search tools, and embedding models

for high-performance document retrieval.

• Work with unstructured and semi-structured data sources (PDFs, HTML, JSON,

SQL, etc.).

• Collaborate with data engineers, ML engineers, and product teams to build end

to-end generative AI solutions.

• Monitor performance, latency, and relevance metrics; iterate on retrieval and

generation models.

• Implement prompt engineering strategies and hybrid approaches (rule-based +

neural) to enhance model reliability.

• Contribute to research and innovation in applied generative AI, and stay up-to

date with the latest in LLM, RAG, and MLOps ecosystems

Key Skills Required:

• Strong experience with RAG architectures and hybrid retrieval systems. •

Solid hands-on knowledge of LLMs (e.g., GPT, Mistral, LLaMA, Claude, DeepSeek, etc.) and embedding models (e.g., SBERT, OpenAI, HuggingFace models).

• Proficiency in machine learning / deep learning using PyTorch, TensorFlow, Hugging Face Transformers, etc.
• Experience with vector databases (e.g., FAISS, Weaviate, Pinecone, Qdrant).
• Experience in text chunking, retrieval scoring, prompt tuning, or LoRA/PEFT methods.
• Strong background in NLP, information retrieval, and knowledge graphs is a plus.
• Comfortable with Python and associated data science stacks (Pandas, NumPy, Scikit-learn).
• Experience working with real-world messy data (PDF parsing, OCR, HTML scraping, etc.)

If interested kindly call share your resume at clarita.fernandes@sperton.com

Regards,

Clarita