AI/ML Engineer - Generative AI

We are looking for an AI/ML Engineer with hands-on experience in Generative AI, Large Language Models (LLMs), NLP, and Retrieval-Augmented Generation (RAG) to design, build, and deploy enterprise-grade AI solutions. The ideal candidate will have strong foundations in Python-based ML development, vector databases, prompt engineering, LLM orchestration, and the Azure AI ecosystem.

1. Generative AI & LLM Engineering

• Build and fine-tune LLM-based applications using models such as GPT, LLaMA, Mistral, Phi, etc.
• Develop custom pipelines for RAG, grounding LLMs on enterprise documents (PDFs, Word, PPT, HTML, images).
• Design robust prompt engineering strategies—system prompts, few-shot examples, evaluation prompts.
• Implement guardrails using safety filters, grounding validation, and hallucination detection.

2. NLP Model Development

• Develop and optimize NLP models for text classification, entity extraction, summarization, Q&A, topic modelling, and semantic search.
• Apply transformer-based architectures (BERT, RoBERTa, T5, LLaMA-based models).
• Build multilingual NLP pipelines where required.

3. RAG Pipelines & Knowledge Engineering

• Create scalable RAG architectures using:
  • Vector databases (Azure AI Search, Pinecone, Weaviate, FAISS).
  • Chunking, metadata tagging, hybrid search, and document embeddings.
• Build connectors for ingestion pipelines (ETL) for structured/unstructured sources.
• Evaluate and optimize retrieval quality (R@K, MRR, context relevancy scores).

4. Azure AI & MLOps

• Use Azure AI Search, Azure OpenAI, Azure Machine Learning, Azure Functions, Data Lake, and DevOps pipelines to build end-to-end solutions.
• Deploy LLM-based APIs, microservices, and inference endpoints using AKS/ACI.
• Implement model evaluation frameworks, monitoring (logging, latency, cost), and lifecycle management.

5. Software Engineering & API Development

• Build Python-based backend services for LLM inference, embeddings, and RAG operations.
• Develop REST APIs and integrate with downstream applications.
• (Nice-to-Have) Build simple UI front-ends using React for demos and internal tools.

6. Collaboration & Documentation

• Work with domain SMEs, product teams, and engineering to convert business needs into AI use cases.
• Document model architectures, design decisions, and best practices.

Required Skills & Qualifications

• 3–5 years of experience in AI/ML, with at least 1–2 years in Generative AI/LLMs/NLP.
• Strong proficiency in Python, PyTorch, Hugging Face Transformers, LangChain/LlamaIndex.
• Hands-on experience with RAG architectures, vector stores, and embedding models.
• Strong understanding of transformer architecture, tokenization, embeddings, and LLM evaluation metrics.
• Experience with Azure AI stack—Azure OpenAI, Cognitive Search/AI Search, Azure ML, Data Lake.
• Familiarity with MLOps tools for tracking, deployment, CI/CD.
• Experience working with unstructured data at scale—documents, text, OCR extractions.

Nice-to-Have Skills

• Experience with React.js for building AI dashboards and internal apps.
• Exposure to knowledge graphs, ontology/metadata design, and structured knowledge retrieval.
• Experience deploying LLMs on edge or private environments (ONNX Runtime, quantized models).
• Familiarity with evaluation frameworks such as Ragas, DeepEval, or custom LLM eval pipelines.

Education

• Bachelor’s/Master’s degree in Computer Science, Engineering, Data Science, AI/ML, or equivalent fields.

BGV:

• Employment with WSP India is subject to the successful completion of a background verification (“BGV”) check conducted by a third-party agency appointed by WSP India.

• Candidates are advised to ensure that all information provided during the recruitment process — including documents uploaded — is accurate and complete, both to WSP India and its BGV partner”.