Job Description
About the Role
We are looking for a motivated entry-level engineer to join our team and help build REST APIs, machine learning, and Large Language Model (LLM)-based applications. This is a fully on-site position, and ideal for someone local who wants to kick-start their career in AI, learn fast, and contribute to real-world projects from day one. This role is challenging and fast-paced, requiring someone who can absorb knowledge quickly, adapt to complex requirements, and execute at high speed. You'll be expected to prototype ideas within a couple of days to test feasibility, and contribute meaningfully to Saa S applications, ML pipelines, and LLM-enabled features under the guidance of experienced engineers. If you are a recent graduate driven by curiosity, action-oriented thinking, and a strong work ethic, this is a rare opportunity to accelerate your growth, work hands-on with cutting-edge AI technologies, and make a real impact from day one.
What You Will Do
- Design and engineer Saa S applications and REST APIs
- Build and test workflows and Agentic AI Applications.
- Integrate open-source LLMs and commercial APIs, into backend services using Lang Chain and other frameworks
- Develop retrieval-augmented generation (RAG) pipelines, including embedding generation, vector store setup, and query orchestration
- Create and maintain prompt templates and toolchains for workflows like multi-turn conversations or auto-tagging of enterprise documents
- Write unit tests and debug issues in LLM-powered features such as semantic search and summarization
- Prototype new ideas rapidly in 1-2 days and iterate with feedback
- Document your work clearly and maintainably
Required Skills
- Strong Python fundamentals
- Prior experience shipping code to production
- Design and engineering experience with Saa S products and REST APIs
- Hands-on experience in building applications with LLMs like GPT, Claude, and LLa MA
- Understanding of embeddings, tokenization, and vector search
- Exposure to Lang Chain, Llama Index, or similar frameworks
- Comfortable with APIs, JSON, and CLI tools
- Ability to build middleware in Node.js and connect to Python backend
- Ability to work fast, prototype quickly, and accept feedback
- Self-driven and persistent problem-solver
What We Offer
A rare, hands-on opportunity to learn real-world AI/LLM development. Daily exposure to LLM models and tools. Direct mentorship from experienced engineers. Fast-paced, execution-focused culture. Performance-based growth for driven candidates. Modest initial compensation with high learning ROI.
How to Apply
Send your resume and a brief note explaining your interest in AI/ML and why this opportunity excites you to If you have worked on any LLM projects - Git Hub links, demos, or code samples are strongly encouraged. As part of the interview process, you will be asked to implement a small prototype to demonstrate your ability to learn quickly, work independently, and apply AI/LLM concepts in code.
We are looking for a motivated entry-level engineer to join our team and help build REST APIs, machine learning, and Large Language Model (LLM)-based applications. This is a fully on-site position, and ideal for someone local who wants to kick-start their career in AI, learn fast, and contribute to real-world projects from day one. This role is challenging and fast-paced, requiring someone who can absorb knowledge quickly, adapt to complex requirements, and execute at high speed. You'll be expected to prototype ideas within a couple of days to test feasibility, and contribute meaningfully to Saa S applications, ML pipelines, and LLM-enabled features under the guidance of experienced engineers. If you are a recent graduate driven by curiosity, action-oriented thinking, and a strong work ethic, this is a rare opportunity to accelerate your growth, work hands-on with cutting-edge AI technologies, and make a real impact from day one.
What You Will Do
- Design and engineer Saa S applications and REST APIs
- Build and test workflows and Agentic AI Applications.
- Integrate open-source LLMs and commercial APIs, into backend services using Lang Chain and other frameworks
- Develop retrieval-augmented generation (RAG) pipelines, including embedding generation, vector store setup, and query orchestration
- Create and maintain prompt templates and toolchains for workflows like multi-turn conversations or auto-tagging of enterprise documents
- Write unit tests and debug issues in LLM-powered features such as semantic search and summarization
- Prototype new ideas rapidly in 1-2 days and iterate with feedback
- Document your work clearly and maintainably
Required Skills
- Strong Python fundamentals
- Prior experience shipping code to production
- Design and engineering experience with Saa S products and REST APIs
- Hands-on experience in building applications with LLMs like GPT, Claude, and LLa MA
- Understanding of embeddings, tokenization, and vector search
- Exposure to Lang Chain, Llama Index, or similar frameworks
- Comfortable with APIs, JSON, and CLI tools
- Ability to build middleware in Node.js and connect to Python backend
- Ability to work fast, prototype quickly, and accept feedback
- Self-driven and persistent problem-solver
What We Offer
A rare, hands-on opportunity to learn real-world AI/LLM development. Daily exposure to LLM models and tools. Direct mentorship from experienced engineers. Fast-paced, execution-focused culture. Performance-based growth for driven candidates. Modest initial compensation with high learning ROI.
How to Apply
Send your resume and a brief note explaining your interest in AI/ML and why this opportunity excites you to If you have worked on any LLM projects - Git Hub links, demos, or code samples are strongly encouraged. As part of the interview process, you will be asked to implement a small prototype to demonstrate your ability to learn quickly, work independently, and apply AI/LLM concepts in code.
Apply for this Position
Ready to join ? Click the button below to submit your application.
Submit Application