LLM / Gen-AI Engineer

We are Hiring LLM / Gen-AI Engineer at Coforge Ltd.

Job Locations:

Experience Required:

Availability:

Job Title: LLM / Gen-AI Engineer

Please share your CV to

WhatsApp 9667427662 for any queries.

Role Summary

LLM / Gen-AI Engineer

production-grade Gen-AI capabilities

Key Responsibilities:-

• Architect and implement

  RAG systems

  : document ingestion chunking embeddings vector store retriever re-ranker prompt assembly LLM inference.
• Productionize LLM applications and workflows:

  scaling, monitoring, observability, and cost optimization

  .

Must-Have Skills:-

• 2+ years hands-on experience

  in NLP/LLM projects (RAG pipelines or LLM fine-tuning).
• Expertise in building

  Retrieval + Re-rank pipelines

  using vector DBs (Milvus, FAISS, Pinecone, Weaviate).
• Strong

  Python programming skills

  ; experience with

  PyTorch / TensorFlow

  .
• Familiarity with

  embeddings

  (creation, evaluation) and

  semantic search

  .
• Practical experience with

  fine-tuning / LoRA / instruction-tuning

  of LLMs (Hugging Face Transformers, OpenAI fine-tune, etc.).
• Knowledge of

  prompt engineering

  and prompt templates.

Nice-to-Have Skills:-

• Experience with

  LangChain, LlamaIndex, Haystack, Promptflow

  , or similar frameworks.
• Exposure to

  cloud ML infrastructure

  : Azure OpenAI, Vertex AI, AWS Bedrock, OpenAI API.
• Familiarity with

  LLM evaluation frameworks

  (human eval, ROUGE, BLEU, BERTScore, truthfulness metrics).

Why Join Us?

• Work on cutting-edge

  Gen-AI solutions

  for enterprise-scale applications.
• Collaborate with a team of AI innovators and thought leaders.
• Opportunity to

  shape the future of AI-driven products

  in a fast-growing domain.