Senior Software Engineer

Aurionpro Solutions Limited is a global leader in advanced technology solutions focused on Banking, Payments, Transit, Data Centre Services, and Government sectors. Leveraging cutting-edge Enterprise AI, we Make comprehensive and scalable technology for clients worldwide. Founded in 1997 and headquartered in Mumbai, Aurionpro is renowned for its deep domain expertise, interconnected intellectual property, global footprint, and a passionate, flexible business approach.

With a client base of over 300 institutions relying on our mission-critical technology, supported by 2,500 professionals, Aurionpro is one of the richest pools of fintech, deep-tech, and AI talent globally. Our culture is built on passion, cross-boundary collaboration, mentorship, and continuous learning, driving us to deliver over 30% growth last fiscal year and crossing the $100 million revenue milestone.

To know more about the organization, you may go through the company website: -

Job Title: AI Engineer – Generative AI Conversational Systems

Experience Level: 3 - 5 years

Job Summary:

We are seeking a highly skilled and research-oriented Machine Learning Data Scientist with deep expertise in Generative AI, Conversational AI, Retrieval-Augmented Generation (RAG), and Agentic systems. The ideal candidate will have hands-on experience with ML/NLP tools and frameworks, and a strong track record of building and deploying scalable AI applications across cloud platforms (AWS, Azure, GCP) and on-premise environments. You will be responsible for developing next-generation AI solutions that enable intelligent conversations, decision support, automation, and seamless human-AI collaboration.

Note:

The following position is excluded from the referral bonus program.

Key Responsibilities

Conversational AI LLM Engineering:

• Design and develop conversational AI models (chat and voice) using LLMs such as GPT, LLaMA, Claude etc.
• Implement RAG pipelines to enhance model performance using contextual and external knowledge sources.
• Build Agentic AI workflows using frameworks like LangGraph to manage complex, multi-step interactions requiring reasoning.
• Perform model fine-tuning, prompt engineering, and embedding optimization.

NLP ML Engineering:

• Perform data cleaning, preprocessing, and analysis on structured and unstructured text using libraries like NLTK, spaCy, and pandas.
• Utilize Hugging Face Transformers for model training, inference, and deployment in production.
• Develop reusable components and prompt strategies for multi-turn dialogues and dynamic intent detection.
• Build and evaluate models for tasks such as text classification, summarization, information extraction, and semantic search.
• Conduct exploratory data analysis and feature engineering across varied datasets.

Deployment Observability:

• Deploy models and services across AWS (SageMaker, Lambda, Bedrock) and on-premises using Kubernetes and Docker.
• Implement monitoring and observability pipelines using tools such as Prometheus, Grafana, OpenTelemetry, and ML observability stacks.
• Ensure production-grade systems are equipped with real-time metrics, traceability, and failover capabilities.

Required Qualifications:

• Bachelor's or Master's degree in Computer Science, Data Science, AI/ML, or a related field.
• Minimum 3+ years of experience in machine learning and NLP, with at least 1–2 years working on LLMs or RAG systems.
• Proficiency in Python and strong experience with NLP libraries such as NLTK, Hugging Face, LangChain, and LangGraph.
• Experience with ML frameworks like PyTorch, TensorFlow, Keras, XGBoost, or Scikit-learn.
• Hands-on expertise in LLM fine-tuning, prompt engineering, and retrieval pipeline optimization.
• Solid understanding of vector search technologies (e.g., FAISS, Pinecone) for semantic retrieval and context enhancement.
• Proven experience in deploying ML solutions in production on cloud and on-prem infrastructure.
• Familiarity with observability, monitoring, and reliability engineering practices for conversational AI systems.
• Experience with RESTful APIs, WebSockets, and real-time event-driven system design.