Full Stack Engineer - AI

About Saarthee:

Saarthee is a Global Strategy, Analytics, Technology and AI product company, where our passion for helping others fuels our approach and our products and solutions. Our diverse and global team work with one objective in mind: Our Customers’ Success.At Saarthee, we are passionate about guiding organizations to wards insights fueled success. That’s why we call ourselves Saarthee–inspired by the Sanskrit word ‘Saarthi’, which means charioteer, trusted guide, or companion. Cofounded in 2015 by Mrinal Prasad and Shikha Miglani, Saarthee already encompasses all the components of Data Analytics consulting. Saarthee is based out of Philadelphia, USA with office in UK and India.

Position: Full Stack Engineer – AI Integration

Location: Gurugram

Work Mode: Hybrid

Min-Max Experience: 4-8 years

Position Summary:

We’re looking for a Full Stack Engineer who goes beyond shipping features — someone who architects, owns, and evolves systems end-to-end.

This role sits at the intersection of scalable backend engineering and modern AI capabilities, where you’ll build intelligent product experience powered by LLMs, RAG pipelines, and agentic workflows.

If you enjoy bridging AI capabilities with production-grade systems — from APIs to UI — this role is for you.

Your Role Responsibilities and Duties:

• Own full stack development — from system design to deployment and iteration
• Architect and build RESTful APIs and microservices across modern stacks
• Develop high-performance, scalable frontend applications using TypeScript (React/Angular)
• Ensure system reliability, observability, and performance optimization
• Identify bottlenecks and optimize for latency, throughput, and cost efficiency
• Collaborate with Product, Design, and Engineering teams to deliver impactful solutions
• Drive engineering excellence through code reviews, testing, and best practices

AI Integration – GenAI Layer

• Integrate and orchestrate LLM APIs (OpenAI, Anthropic, Gemini, open-source models)
• Build RAG pipelines including embeddings, vector databases, and retrieval systems
• Design and implement Agentic AI workflows using frameworks like LangChain or LlamaIndex
• Own prompt engineering, versioning, and evaluation pipelines
• Build AI-aware APIs with streaming, retries, fallbacks, and cost control
• Handle non-deterministic AI outputs with robust system design

Required Skills and Qualifications:

• BE / B.Tech in Computer Science or related field
• 4–8 years of experience in full stack development (IC role)

Core Technologies

• Languages: TypeScript, Node.js, Java, Python, or Go
• Frontend: React / Angular, TypeScript
• Backend: Microservices, Distributed Systems, API Design
• Databases: PostgreSQL, MongoDB, Redis
• Cloud & Infra: AWS / GCP / Azure, Docker, Kubernetes, CI/CD

GenAI (Mandatory)

• Hands-on experience with LLM APIs
• Strong understanding of RAG (Retrieval-Augmented Generation)
• Experience with Agentic AI / multi-agent systems
• Familiarity with LangChain, LlamaIndex, embeddings, and vector databases

Foundations

• Strong in Data Structures & Algorithms
• Solid system design and problem-solving skills
• Clean coding practices, testing, and documentation