AI Engineer

Nomia; Bengaluru; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Nomia is transforming tail spend procurement with an AI-powered SaaS platform. We are building intelligent systems for knowledge retrieval and language understanding across the Nomia platform, focusing on NLP pipelines, RAG architectures, and LLM integration.

The role involves designing NLP models, implementing RAG pipelines with LangChain, integrating large language models, and delivering production-ready AI services in Python. Hybrid work with office days per week.

Qualifications

• 3–6 years of hands-on AI, ML and NLP experience.
• Proficiency in Python and AI/NLP libraries (NLTK, spaCy, Transformers, scikit-learn, PyTorch/TensorFlow).
• Experience with LangChain and RAG architecture is essential.
• Strong understanding of vector databases and prompt engineering.
• Familiarity with LLM APIs and retrieval/semantic similarity techniques.

Responsibilities

• Design and develop ML models with a focus on NLP use cases.
• Implement and optimize RAG pipelines using LangChain and vector stores.
• Fine-tune and integrate large language models into workflows and apps.
• Develop scalable AI services using Python and relevant libraries.
• Preprocess data, tokenize, vectorize with NLTK, spaCy, Transformers.
• Build evaluation frameworks for accuracy, latency, and relevance.

Skills

NLP

Python

LangChain

RAG pipelines

Vector databases

LLM APIs

Prompt engineering

Tools

FAISS

Pinecone

Weaviate

Transformers

PyTorch

TensorFlow

Job description

Nomia is transforming the way organizations manage tail spend procurement.

Our AI-powered SaaS platform combines cutting-edge technology with deep human procurement expertise to simplify sourcing, drive compliance, and unlock measurable value.

With a fast-growing global customer base and teams across London, Dubai, Singapore, Krakow, Chicago, and India, we’re building a rocket ship for growth, and we’re looking for passionate, high-impact people to join us.

The Role

This role is critical to driving innovation and building intelligent systems that enable knowledge retrieval and language understanding across the Nomia platform.

You will focus on implementing NLP pipelines, Retrieval-Augmented Generation (RAG) architectures, and integrating large language models to solve real-world business problems at Nomia.

Roles and Responsibilities

• Design and develop machine learning models, with a focus on Natural Language Processing (NLP) use cases
• Implement and optimize Retrieval-Augmented Generation (RAG) pipelines using tools like Langchain and vector databases
• Fine-tune and integrate large language models (e.g., OpenAI, Llama, Cohere) into internal workflows and applications
• Develop scalable and production-ready AI services using Python and relevant libraries
• Perform data preprocessing, tokenization, stemming, and vectorization using libraries such as NLTK, spaCy, and Transformers
• Design and maintain evaluation frameworks to measure the accuracy, relevance, and latency of NLP models
• Collaborate with data engineers, backend developers, and product managers to integrate AI models into applications
• Conduct experiments and ablation studies to validate model choices and configurations
• Manage, monitor, and maintain model performance in production environments
• Document model assumptions, training pipelines, APIs, and deployment steps clearly
• Stay abreast of advancements in LLMs, embeddings, and retrieval techniques
• Participate in code reviews, technical discussions, and cross-functional meetings
• Identify and solve practical NLP problems in areas like question answering, summarization, entity extraction, and semantic search
• Support continuous improvement by automating retraining pipelines and incorporating user feedback into iterative model refinement

Qualifications/Skills

• 3–6 years of hands-on experience in AI, Machine Learning and NLP
• Proficient in Python, with strong command of AI and NLP libraries (e.g., NLTK, spaCy, Transformers, scikit-learn, PyTorch/TensorFlow)
• Experience with Langchain and RAG architecture is essential
• Strong understanding of vector libraries & databases (e.g., FAISS, Pinecone, Weaviate)
• Familiarity with LLM APIs and prompt engineering
• Exposure to retrieval, ranking, and semantic similarity techniques
• Proficient in writing clean, maintainable code and well-documented ML pipelines
• Experience with integrating with AI models using RESTful APIs or microservices

General Information

• Adhere to Nomia’s data protection and information security policies at all times.
• Promote diversity and inclusion in line with Nomia’s core values.
• This is a hybrid role, with three office days per week required, potentially more during training or as requested by your supervisor.
• Contribute to continuous improvement in systems and processes.
• Please note that this role description is a guideline, and duties may evolve over time.