AI/ML Engineer

Role : AI/ML Engineer (LLM & Agent Systems)

About the Job :

We are seeking a highly skilled and motivated AI/ML Engineer with a specialization in Large Language Models (LLMs) and multi-agent systems.

The ideal candidate will have a passion for building innovative and intelligent applications that leverage the latest advancements in generative AI.

You will be responsible for the end-to-end design, development, and deployment of sophisticated AI agents, RAG pipelines, and LLM-powered services.

This is a hands-on role where you will be expected to architect solutions, write high-quality code, and contribute to all phases of the software development lifecycle, from initial concept to production deployment and monitoring.

You will work within a fast-paced, collaborative environment, pushing the boundaries of what's possible with AI.

Key Responsibilities

- Design & Development : Architect and build complex, multi-agent systems using frameworks like LangGraph and CrewAI to solve challenging business problems.

- RAG Pipeline Engineering : Develop and optimize advanced RAG (Retrieval-Augmented Generation) architectures, including document processing, vectorization, hybrid search, and contextual reranking to improve the accuracy and relevance of LLM responses.

- Prompt Engineering & Model Tuning : Expertly craft prompts and utilize various LLM APIs (OpenAI, Claude, Gemini) to guide model behavior.

- Experiment with and integrate open-source models (e.g., Mistral, LLaMA) for specific use cases.

- Infrastructure & Deployment : Implement robust, scalable, and observable production systems.

Build and deploy REST APIs using frameworks like FastAPI, containerize applications with Docker, and set up CI/CD pipelines.

- MLOps & Evaluation : Establish and maintain MLOps practices, including rigorous prompt and model evaluation, A/B testing, and telemetry to ensure the reliability and performance of AI systems in production.

- Collaboration : Work closely with product managers, designers, and other engineers to translate business requirements into technical specifications and deliver high-impact solutions.

- Leadership & Ownership : Take full ownership of projects from inception to completion, demonstrating a strong ability to work independently, manage timelines, and communicate progress effectively.

Required Skills & Qualifications :

- Experience : 3+ years of professional experience in software engineering, data science, or a related field, with a significant focus on AI/ML.

- Programming : Advanced proficiency in Python is a must.

Experience with Typescript/Node.js is a nice-to-have.

- AI Frameworks : Hands-on, demonstrable experience with LangGraph, CrewAI, LangChain, and LlamaIndex.

- Agent Systems : Proven track record of designing and building task-oriented AI agents with capabilities such as memory management, effective tool use, multi-step planning, and inter-agent communication.

- RAG Architecture : Deep understanding of the full RAG pipeline, including document loaders, various chunking strategies, vector embedding models, hybrid search techniques (BM25 + vector search), and contextual reranking algorithms.

- LLM Tooling : Practical experience with commercial LLMs like OpenAI GPT-4/4o, Claude, and Gemini, as well as integrating and fine-tuning open-source models from platforms like Hugging Face.

- Infrastructure : Expertise in working with various databases, including Vector DBs (e.g., Weaviate, Pinecone, Qdrant, Elasticsearch), and traditional databases like Postgres and MongoDB.

- MLOps : Practical experience with prompt engineering, model evaluation metrics, A/B testing frameworks, and setting up telemetry and observability for AI applications.

- Deployment : Strong skills in building and deploying production-ready applications.

Experience with REST APIs, FastAPI, Docker, and CI/CD pipelines is essential.

Other :

- Strong written and verbal communication skills.

- Ability to work independently and manage initiatives end-to-end with minimal supervision.

- A proactive and curious mindset, with a desire to stay current with the latest developments in the AI field