Key Responsibilities
Design, develop, and optimize Python-based AI applications for Generative AI use cases.
Build, fine-tune, and deploy LLMs (LLAMA, OpenAI, Mistral, etc.).
Develop and standardize AI Copilot frameworks.
Build Agentic AI systems with multi-agent reasoning, tool calling, and orchestration.
Design and manage RAG pipelines using Qdrant DB, Chroma DB, and other Vector Databases.
Implement Deep Learning models for image processing and multimodal AI.
Perform image preprocessing, OCR, document AI, and vision model integration.
Develop audio processing pipelines, including:
Speech-to-Text (STT) using Whisper
Audio preprocessing and noise handling
Build real-time voice & AI interaction systems using WebRTC.
Optimize workloads on AWS & Azure GPU instances, including GPU and memory management.
Develop scalable ETL pipelines for data ingestion, embeddings, and training workflows.
Deploy and maintain AI services in Linux-based settings.
Collaborate with cross-functional teams to deliver production-ready AI systems.

Must-Have Skills
Expert-level Python programming.
Solid hands-on experience with Generative AI & LLMs.
Experience working with LLAMA or equivalent models.
Hands-on experience with Vector Databases:
Qdrant DB
Chroma DB
FAISS, Pinecone, Milvus, or similar




Robust understanding of GPU computing, memory optimization, and performance tuning.
Experience with AWS GPU EC2 and Azure GPU services.
Solid experience with Deep Learning frameworks (PyTorch, TensorFlow).
Strong knowledge of Image Processing.
Hands-on experience with Audio Processing, including Whisper.
Experience building real-time audio pipelines using WebRTC.
Proficiency in Linux environments.
Working knowledge of SQL databases.

Good-to-Have (Bonus) Skills
Experience with LLM orchestration frameworks:
LangChain
LlamaIndex
Haystack
Experience with Agentic AI frameworks.
API development using FastAPI, Streamlit, or similar.
Experience implementing CI/CD pipelines for AI/ML workloads.
Knowledge of ETL pipelines and data engineering.
Familiarity with multimodal LLMs (text + image + audio).
Experience across AWS services (S3, API Gateway, EC2) and Azure services.
Exposure to multiple GenAI models (OpenAI, LLAMA, Mistral, Google Bard, etc.).

Nice-to-Have
Experience with real-time AI assistants and voice bots.
Knowledge of RAG architectures, AI security, and governance.
Containerization experience (Docker, Kubernetes).
MLOps
Monitoring, logging, and observability for AI systems.

📌 Senior Artificial Intelligence Engineer Coimbatore
🏢 Nexa Office Infosystems
📍 Coimbatore