Senior Ai Engineer Bayantech

- Design, develop, and deploy AI agents capable of performing autonomous tasks.

- Build and fine-tune solutions using LLMs (e.g., OpenAI, Gemini, Claude, Mistral, LLaMA).

- Proficient in Retrieval-Augmented Generation (RAG) systems and experienced with vector databases, leveraging these technologies to enhance AI model performance and scalability

- Implement communication between agents using agent orchestration frameworks.

- Automate workflows for sales, project management, accounting, and localization.

- Collaborate with backend and frontend teams to integrate AI services.

- Conduct prompt engineering and evaluation of model outputs.

- Ensure the scalability and performance of AI systems in production environments.

Requirements:

7+ years of experience in AI, NLP, or ML system development.

Proven expertise in LLM training and fine-tuning (GPT, LLaMA, Mistral, Falcon, etc.).

Hands-on experience with RAG pipelines and vector databases (FAISS, Pinecone, Qdrant, Weaviate).

Strong Python skills and proficiency in PyTorch or TensorFlow.

Experience building and deploying custom AI models for text or speech.

Knowledge of transformer architectures, tokenization, and quantization.

Practical use of OpenAI API, Hugging Face, and LangChain.

Experience integrating models via FastAPI, Flask, or NestJS microservices.

Familiarity with MLOps, Docker, CI/CD, and cloud environments (AWS/GCP/Azure).

Strong foundation in deep learning, statistics, and data preprocessing.

Excellent communication and leadership skills to guide junior AI engineers.

Nice to Have:

Experience with speech models (Deepgram, Whisper, Piper).

Familiarity with Twilio, Asterisk, or WebSocket-based AI streaming.

Knowledge of localization automation and translation quality scoring.

Understanding of LangGraph, CrewAI, or multi-agent frameworks.

Exposure to multi-GPU training and on-premise optimization.