About The Role
We are seeking a skilled AI/ML Engineer to design, build, and deploy production-grade AI systems powered by Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and core Machine Learning. The ideal candidate will enjoy working close to data, models, and algorithms, and will have a passion for optimizing retrieval latency and agent decision-making paths. Experience in end-to-end ownership from data to deployment is essential.
Key Responsibilities
- Design, build, and optimize RAG pipelines (chunking, embeddings, vector search, re-ranking, and evaluators) with a focus on low latency.
- Build robust data pipelines to ingest, clean, and chunk large-scale unstructured data (PDFs, HTML, logs).
- Improve LLM response quality, grounding, and hallucination reduction.
- Web search data retrieval for LLMs
- External data ingestion and management for AI systems
- Small Language Models (SLMs) development
- Data pipelines for external sources (APIs, web scraping, streaming data)
- Model inference optimization and latency reduction
- Train and evaluate machine learning models, including classification, regression, and clustering.
- Develop scalable architectures for agent tool-calling and SQL integration.
- Collaborate on improving HNSW, semantic ranking, and recall metrics.
- Deploy and optimize AI systems for low-latency and cost-efficient inference.
Required Skills And Qualifications
- 2–3 years of relevant experience in AI/ML engineering.
- Proven experience in Python and proficiency with frameworks like LangChain, LlamaIndex, Milvus, Types of RAGs and GenAI libraries for Agentic AI & orchestration.
- Hands-on experience deploying, optimizing, and fine-tuning open-source models (e.g., Llama 3, Deepseek, Mixtral) using HuggingFace Transformers and vLLM.
- Strong problem-solving skills with a focus on optimizing retrieval latency.
- Experience working with large datasets, Knowledge Graphs, SQL, and production ML systems.
- Ability to build scalable data pipelines for processing unstructured datasets.
Preferred Qualifications
- Experience developing models using PyTorch or TensorFlow.
- Familiarity with LLM fine-tuning techniques (e.g., LoRA, adapters).
- Knowledge of MLOps practices and experiment tracking tools.
Why Join Us
- Work on real-world AI and LLM systems used in production.
- Take end-to-end ownership of projects from data processing to deployment.
- Collaborative environment focused on building scalable RAG and LLM architectures.
- Strong technical ownership and culture of growth.
- Career growth opportunities
- Opportunity to mentor and be mentored
