Senior Consultant

We are seeking Data Scientists/Data Engineers/Generative AI Engineers with strong expertise in LLMs and LLM modelling.

Key Responsibilities:

• Build GenAI applications using LLMs (OpenAI, bedrock, huggingface etc.)
  
• Develop RAG pipelines: chunking, embeddings, retrieval optimization,rerankers
  
• Implement prompt engineering, evaluation, and guardrails
  
• Fine-tune and optimize open-source models (LoRA/PEFT)
  
• Design APIs using FastAPI/Flask and integrate with microservices
  
• Work with vector databases (Weaviate, Pinecone, Qdrant)
  
• Deploy AI workloads on cloud (AWS/Azure/GCP)
  
• Monitor model quality, hallucination rates, and performance metrics

Required Skills:

• Strong Python development background
  
• Hands-on experience with:
  
• LLM APIs: OpenAI, Azure OpenAI, Anthropic, Google Gemini, Groq
  
• Open-source models: Llama, Mistral, Mixtral, Falcon, Gemma
  
• Fine-tuning frameworks: Hugging Face, PEFT, LoRA
  
• Vector DBs: Weaviate, Pinecone, Qdrant, etc.
  
• RAG pipelines: LangChain, LlamaIndex, Haystack (or custom)
  
• Embedding models, chunking techniques, search tuning
  
• FastAPI / Flask backend development
  
• Cloud: AWS S3, EC2, Lambda, Bedrock (added advantage)

Good to Have:

• Experience with multi-agent frameworks (CrewAI, LangGraph, Autogen).
  
• Knowledge of model quantization, GPU optimization, and inference acceleration.
  
• Familiarity with DevOps tools (GitHub Actions, Terraform, Docker, Helm).
  
• Exposure to security compliance (PII masking, policy enforcement, RBAC).
  
• Basic understanding of front-end (React) helpful but optional.