Bitsclan is seeking a Python Developer with hands-on experience in AI and Large Language Models (LLMs) to join our growing engineering team. In this role, you will work on designing, developing, and scaling intelligent applications that leverage machine learning, NLP, and generative AI capabilities. You will collaborate closely with cross-functional teams to build backend services, integrate AI models, and deliver innovative product features.
Key Responsibilities:
- Design, develop, and maintain scalable and secure Python-based backend applications.
- Implement, fine-tune, and deploy LLM- and AI-powered features into production environments.
- Work with frameworks such as Django, Flask, or FastAPI to build robust APIs and services.
- Collaborate with data scientists and ML engineers to integrate AI/ML pipelines.
- Optimize AI model inference performance and application scalability.
- Conduct code reviews, ensure best coding practices, and mentor junior engineers when needed.
- Integrate with databases, third-party APIs, and cloud-based services.
- Troubleshoot, debug, and enhance existing applications.
- Participate in architectural discussions and contribute to technology strategy.
- Stay abreast of advancements in AI, machine learning, and emerging LLM technologies.
Key Requirements:
- Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a related field.
- 2+ years of professional Python development experience.
- Strong experience with Django, Flask, OR FastAPI.
- Hands-on experience working with LLMs, NLP models, AI libraries (e.g., Hugging Face, LangChain, OpenAI API, Transformers).
- Solid understanding of RESTful APIs, microservices, and software architecture principles.
- Strong database knowledge: PostgreSQL, MySQL, MongoDB, Redis, etc.
- Proficiency with Git (GitHub/GitLab) for version control.
- Familiarity with Docker, Kubernetes, and CI/CD pipelines.
- Strong problem-solving and debugging skills.
- Excellent communication and teamwork abilities.
Preferred Skills (Nice to Have):
- Experience with model fine-tuning, embeddings, RAG pipelines, or vector databases (Pinecone, Weaviate, ChromaDB, etc.).
- Knowledge of asynchronous programming (AsyncIO, Celery).
- Experience with cloud environments (AWS, Azure, GCP).
- Knowledge of TDD, automated testing, and Agile/Scrum workflows.
Job Type: Full-time
Work Location: In person