- Company Name
- Lendbuzz
- Job Title
- Software Engineer (Machine Learning - LLMs)
- Job Description
-
**Job Title:** Software Engineer (Machine Learning – LLMs)
**Role Summary:**
Design, develop, and optimize large‑language‑model (LLM) powered conversational agents. Collaborate with ML researchers and product teams to ship high‑impact features, own critical components of the conversational AI stack, and ensure reliability, scalability, and superior user experience.
**Expectations:**
- Deliver production‑ready code and end‑to‑end pipelines in a fast‑moving environment.
- Work independently while coordinating cross‑functionally with ML, backend, and product stakeholders.
- Maintain data quality and model performance through continuous monitoring and iterative improvement.
- Contribute to documentation, experimentation standards, and knowledge sharing.
**Key Responsibilities:**
- Implement and maintain LLM‑based conversational agents, focusing on reliability and UX.
- Evaluate, fine‑tune, and deploy LLM models via REST APIs and internal microservices.
- Develop prompt engineering, retrieval‑augmented generation (RAG), tool‑use pipelines, and conversation orchestration logic.
- Integrate emerging real‑time voice, streaming, and multi‑modal technologies.
- Analyze model outputs, user interactions, and system metrics to drive improvements.
- Build and curate high‑quality datasets, including cleaning, preprocessing, labeling, and benchmarking for NLP tasks.
- Ensure data accuracy, reproducibility, and lifecycle reliability.
- Collaborate on deployment best practices, monitoring, and scaling of LLM services in cloud environments.
- Produce internal documentation, experiment tracking, and model evaluation frameworks.
**Required Skills:**
- Strong Python programming; proficient with ML/data libraries (PyTorch, Pandas, NumPy, Scikit‑learn).
- Hands‑on experience with NLP techniques and LLM concepts.
- Ability to design, implement, and troubleshoot backend/ML pipelines.
- Solid problem‑solving skills and comfort working autonomously.
- Familiarity with cloud platforms (preferably AWS) for model/application deployment.
- Bonus: experience with real‑time systems, WebSockets/streaming, vector databases, RAG pipelines, or ML evaluation frameworks (e.g., Genesys, Twilio).
**Required Education & Certifications:**
- Master’s degree in Artificial Intelligence, Computer Science, or a related technical field.
- Relevant professional experience (2+ years) in software engineering, data processing, or ML pipeline development.