AI Engineer (LLMs & RAG Pipelines)

Location : Gurgaon (Work from Office, 5 Days a Week)

Employment Type : Full-Time

About Us :

We are transforming global logistics and operational visibility through our advanced B2B SaaS supply chain analytics platform. Beyond standard dashboards, we are actively deploying production-grade LLM pipelines, vector search workflows, and generative AI features into our ecosystem to help enterprise clients query supply chain data using natural language. If you are passionate about applied AI and want to build intelligent systems in a fast-paced environment, you will thrive in our Gurgaon office.

The Role :

We are seeking a sharp, hands-on AI Engineer with 2 years of experience to help design, fine-tune, and scale our artificial intelligence capabilities. You will work closely with our core engineering team to build RAG (Retrieval-Augmented Generation) architectures, integrate vector databases, and optimize LLM workflows tailored to supply chain intelligence.

Key Responsibilities :

- RAG Implementation : Build and scale Retrieval-Augmented Generation frameworks connecting enterprise supply chain data to vector databases (Qdrant/Pinecone).

- Prompt & LLM Optimization : Optimize prompt engineering workflows, manage token usage, and evaluate performance across various LLM providers.

- Inference Endpoints : Develop and maintain low-latency AI inference microservices using Python and FastAPI.

- Model Evaluation : Test and benchmark open-source or commercial models for domain-specific accuracy in logistics forecasting and automated query resolution.

- System Integration : Seamlessly bridge AI pipelines with our existing backend infrastructure.

What We Are Looking For (Requirements) :

- Experience : Around 2 years of professional software/ML engineering experience with a strong focus on applied AI and LLMs.

- Technical Stack : Deep proficiency in Python, FastAPI, and asynchronous programming.

- AI Ecosystem : Hands-on experience with LangChain, LlamaIndex, vector databases, and major LLM APIs.

- Engineering Mindset: Solid understanding of API design, Docker containerization, and database integration (PostgreSQL/MySQL).

- Work Arrangement: Fully committed to working from our Gurgaon office, 5 days a week.

What We Offer :

- Competitive Compensation : Attractive salary bracket paired with performance bonuses.

- Cutting-Edge Stack : Hands-on experience building production AI and vector search systems.

- In-Office Energy : Collaborative, high-energy office environment in Gurgaon.

- Wellness & Benefits : Comprehensive health insurance coverage.

Our Hiring Process :

- Initial Screening : 30-minute introductory chat with our recruitment team.

- Technical Assessment : Practical AI/Python coding or RAG integration task.

- In-Person Interview : Technical deep dive at our Gurgaon office.

- Final Chat & Offer : Welcome aboard!