About Trantor

Trantor is a technology services company focused on outsourced product development and digital re-engineering.  Leveraging our CaptiveCoE™ engagement model, we operate as a seamless extension of our clients’ teams to provide rapid scalability with predictable budgets.  Founded in 2012, Trantor has worked with customers across Tech, FinTech, Media & Cyber Security industries. We have centers in the US, India, Canada, and Costa Rica. We are consistently rated as the #1 employer in the region with the ability to attract and retain technical talent. Our commitment to excellence and impactful results has translated to long-term relationships and value for our clients and solution partners Please visit us at:  https://trantorinc.com

Job Description:

We are looking for a hands-on technical lead with strong Python expertise and a deep understanding of Large Language Model (LLM) integration to lead the design, development, and deployment of AI-powered solutions. This role requires a balance of technical leadership, architecture design, and hands-on coding to ensure high-quality, scalable, and efficient AI-driven applications.
You will collaborate closely with product, data science, and MLOps teams to integrate LLMs into real-world applications, optimize performance, and guide the team in best practices for AI system design.

Job Role & Responsibilities

• Lead the development and integration of Python-based applications with LLMs (OpenAI, DeepSeek, Anthropic, LLaMA, etc.).
• Architect and implement LLM pipelines including prompt engineering, retrieval-augmented generation (RAG), fine-tuning, and evaluation.
• Design scalable microservices and APIs for AI features.
• Collaborate with MLOps teams to deploy and monitor AI models in production.
• Ensure performance optimization, cost efficiency, and security in LLM workflows.
• Guide the team on Python best practices, code reviews, and technical problem-solving.
• Stay updated on emerging AI/LLM advancements and propose adoption where beneficial.

Required Skills

• Strong proficiency in Python (FastAPI, Flask).

• Solid experience with LLM integration (OpenAI API, Hugging Face Transformers, LangChain, LlamaIndex).
• Understanding of RAG pipelines (vector databases like Pinecone, Weaviate, FAISS, Milvus).
• Experience with prompt engineering & evaluation techniques.
• Knowledge of MLOps tools (MLflow, Kubeflow, Langfuse) and deployment on AWS/GCP/Azure.
• Familiarity with containerization and orchestration (Docker, Kubernetes).
• Strong grasp of REST APIs, GraphQL, and microservices architecture.
• Knowledge of model fine-tuning and performance optimization.
• Excellent leadership and mentoring abilities.
• Strong problem-solving and analytical skills.
• Ability to work in a fast-paced, evolving AI environment.
• Bachelor’s or Master’s in Computer Science, AI/ML, or a related field. Equivalent experience is also welcome.

Nice-to-Have

• Experience with agentic AI or Model Context Protocol (MCP).
• Background in data pipelines (ETL, streaming data).
• Exposure to AI security & compliance practices.
• Prior work in scalable enterprise AI products.