Company: NeuraNX.ai

Location:
Chennai

Experience:
3–5 years Employment Type: Full-time Role OverviewWe are looking for a skilled AI/ML Engineer with strong Python development experience to join our engineering team. The ideal candidate should have hands-on experience working with large language models, Hugging Face models, AI inference frameworks and production-grade Python applications.

Key Responsibilities
• Develop AI and machine-learning applications using Python.
• Integrate and deploy open-source LLMs and multimodal models.
• Build scalable inference APIs using FastAPI or similar frameworks.
• Work with Hugging Face Transformers and PyTorch.
• Implement streaming responses, batching and asynchronous processing.
• Optimise models for latency, throughput and memory utilisation.
• Develop benchmarking and evaluation pipelines.
• Monitor model performance, accuracy and inference metrics.
• Troubleshoot model-loading, GPU-memory and runtime issues.
• Write clean, modular, secure and well-tested Python code.
• Research and evaluate new AI models and inference technologies. Required Skills
• 3–5 years of experience in Python development or AI/ML engineering.
• Solid programming skills in Python.
• Experience with FastAPI, Flask or similar frameworks.
• Hands-on experience with PyTorch and Hugging Face Transformers.
• Experience deploying or serving large language models.
• Understanding of:
• Tokenisation
• Attention and context length
• KV cache
• Quantisation
• Continuous batching




• Streaming inference
• Experience with at least one inference framework:
• vLLM
• SGLang
• NVIDIA Triton
• TensorRT-LLM
• KServe
• Ray Serve
• Experience with REST APIs, WebSockets or Server-Sent Events.
• Familiarity with PostgreSQL, Redis or similar databases.
• Strong debugging and problem-solving skills. Preferred Skills
• Experience working with NVIDIA GPUs and CUDA.
• Knowledge of INT8, INT4, AWQ or GPTQ quantisation.
• Experience with embedding, reranking, OCR, speech or vision-language models.
• Experience building Python SDKs or reusable AI libraries.
• Familiarity with model benchmarking and load testing.
• Contributions to open-source AI projects will be an advantage. QualificationsBachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science or a related field. Candidates with strong practical experience and demonstrable AI projects will also be considered. What We Are Looking For
• A hands-on engineer who can convert AI models into reliable applications.
• Strong ownership from design through implementation.
• Ability to independently research and integrate open-source AI technologies.
• Good communication and documentation skills.
• Interest in working in a fast-moving product engineering environment. Application DetailsCandidates may share their resume along with:
• GitHub or portfolio link
• Details of AI/ML projects
• Current location
• Notice period
• Current and expected compensation

📌 AI/ML Engineer – Python (Chennai)
🏢 NeuraNx.ai
📍 Chennai