AI Engineer (1 Year Exp)

Overview

Job Title: AI Engineer (1 Year Experience)

Location: Coimbatore
Job Type: Full-time
Experience Level: 1-2 years in AI/ML

Responsibilities:

As an AI Engineer at Neuronest AI, you will be responsible for advancing our conversational AI solutions, optimizing LLM-based systems, and developing multi-agent workflows. Your contributions will directly impact how we build intelligent agents, enhancing automation and decision-making across various use cases.

LLM Development & Optimization:

• Fine-tune and deploy state-of-the-art LLMs (GPT, LLaMA, Mistral, Falcon, etc.) using techniques like LoRA, QLoRA, and GPTQ.
• Reduce hallucinations and improve response accuracy with Retrieval-Augmented Generation (RAG), prompt engineering, and memory management.

Conversational AI & Multi-Agent Workflow:

• Implement multi-turn dialogue management systems and context-aware chatbots.
• Design and develop agentic workflows using LangGraph, LangChain, and AutoGen.
• Build multi-agent collaboration systems to automate complex tasks, enabling LLM-based reasoning and planning.

Knowledge Retrieval & Vector Search:

• Build and maintain vector search pipelines using FAISS, Pinecone, Weaviate, and ChromaDB.
• Integrate these pipelines with both structured (SQL, PostgreSQL) and unstructured (MongoDB, ElasticSearch) databases.

Deployment & MLOps:

• Develop scalable LLM APIs using frameworks such as FastAPI, Flask, or Node.js.
• Deploy applications using Docker, Kubernetes, and cloud platforms (AWS, Azure, GCP).
• Implement MLOps tools such as DVC, MLflow, and Airflow for model tracking, versioning, and automation.

Multi-Agent Coordination & Workflow Optimization:

• Implement agent-to-agent communication for dynamic workflows and automated decision-making.
• Optimize agent behavior powered by LLMs, focusing on reducing response time and enhancing contextual accuracy.
• Design autonomous task execution pipelines that adapt to user intent and real-world scenarios.

Performance & Monitoring:

• Benchmark system performance using BLEU, ROUGE, and latency metrics.
• Optimize chatbot responses through A/B testing and real-time monitoring with tools such as Prometheus, Grafana, and the ELK stack.

Required Skills:

LLM Expertise:

• Experience in fine-tuning and deploying LLMs (Hugging Face, OpenAI, LLaMA, Mistral).
• Knowledge of transformers, embeddings, LoRA, QLoRA, and GPTQ.

Multi-Agent AI & Orchestration:

• Proficiency in LangGraph, AutoGen, LangChain, and developing multi-agent coordination systems.

NLP & Chatbot Development:

• Experience building and optimizing multi-turn chatbots with frameworks such as LangChain, LlamaIndex, RAG, spaCy, NLTK, and SentenceTransformers.

Data & Vector Search:

• Hands-on experience with vector search technologies such as FAISS, Pinecone, and ChromaDB.
• Proficiency in both structured (SQL, PostgreSQL) and unstructured (MongoDB, ElasticSearch) data search.

Software Engineering:

• Strong proficiency in Python, FastAPI, Flask, and deployment using Docker and Kubernetes.
• Familiarity with MLOps tools (DVC, MLflow, Airflow) for model tracking and automation.

Why Neuronest AI?
At Neuronest AI, we provide an innovative and collaborative environment where AI experts can thrive. You'll work with cutting-edge technologies and contribute to products that make a meaningful impact in the AI and machine learning fields.

Job Type: Full-time

Pay: From ₹25,000.00 per month

Schedule:

• Day shift

Experience:

• LLM: 1 year (Required)
• AI/ML: 1 year (Required)

Work Location: In person