Who Are We?
As a group of passionate technology developers, successful entrepreneurs and industry experts, SiftMed is scaling and growing quickly. We are looking for a Senior Software Engineer (AI and Document Processing) with a passion for developing advanced technology and constantly pushing the envelope.
SiftMed is an AI driven system that processes, organizes, and categorizes medical files. Driven by a mission to extract facts in medical data that can change lives - the company focuses on improving access to critical information, empowering legal teams and medical experts to quickly and accurately find previously hidden key facts in medical data.

WHAT WE’RE LOOKING FOR:

We’re looking for a Senior Software Engineer who can fine-tune and optimize large language models, build production-grade APIs and services around them, and scale deployments on AWS. You should bring deep hands-on LLM experience, strong Python engineering skills, and a bias for shipping real-world AI-based products quickly and reliably. If you’re passionate about pushing the boundaries of what LLMs can do at scale, this is your role.

REQUIRED SKILLS:

• 5+ years of experience in backend or systems engineering, with at least 2 years working on LLM or AI-powered applications.
• Strong programming skills in Python, with frameworks like FastAPI, LangChain, or Transformers.
• Proven experience deploying LLMs or ML systems to production using Docker and AWS (ECS, S3, Lambda, SageMaker, Bedrock).
• Familiarity with LLM orchestration techniques such as prompt routing, chaining, or retrieval-based augmentation.
• Understanding of performance optimization techniques for real-time inference and large-scale document processing.
• Strong fundamentals in distributed systems, APIs, observability, and reliability.

• Design and build LLM-backed pipelines (GPT-family, Llama, Mistral, Claude, etc.) for document analysis at scale.
• Implement retrieval-augmented generation (RAG), prompt engineering, and lightweight fine-tuning (e.g., LoRA, adapters).
• Develop and deploy production-grade APIs and microservices that serve LLM-based features.
• Optimize inference: apply batching, caching, model quantization, and latency reduction techniques.
• Build fault-tolerant, scalable, high-availability systems using AWS services like ECS, Lambda, S3, SageMaker, and Bedrock.
• Collaborate closely with backend, frontend, and product teams to ship and iterate quickly.
• Own the full lifecycle of AI features: design → implementation → deployment → monitoring.