Senior/Lead AI Engineer (LLM)

Impressit is looking for a Senior / Lead AI Engineer (LLM) to join a cross-functional product team working on an AI-powered healthcare billing platform. The product helps automate the medical invoice coding process by analyzing unstructured clinical data, recommending billing codes using locally hosted Large Language Models, and integrating validated results into the client's existing management systems. This is a great opportunity to build a meaningful AI solution with real-world impact while taking ownership of technical decisions and working directly with an international client.

What do we expect?

• 4+ years of commercial experience as an AI Engineer, ML Engineer, or Software Engineer working with LLM-based solutions
• Strong hands-on experience with Python for building data ingestion, processing, and AI pipelines
• Experience building supporting frontend applications with React
• Solid experience with Large Language Models, including researching, evaluating, benchmarking, and selecting the most suitable models for production use
• Hands-on experience with local/self-hosted LLMs and inference frameworks such as Ollama, vLLM, llama.cpp, LM Studio, or similar technologies
• Strong understanding of prompt engineering, model evaluation, and optimization techniques for accuracy, latency, and resource utilization
• Experience integrating AI solutions through REST APIs and Model Context Protocol (MCP)
• Solid experience with SQL and/or NoSQL databases
• Proven ability to write automated tests and maintain high code quality
• Good understanding of CI/CD practices
• Excellent problem-solving, analytical, and debugging skills
• Strong Computer Science fundamentals (algorithms, data structures, OOP, software architecture)
• Excellent communication skills with previous experience working directly with clients and translating business needs into technical solutions
• Ability to work independently, make architectural decisions, and take full ownership of deliverables
• Upper-Intermediate or higher level of English

What will you do?

• Build AI-powered data ingestion pipelines that collect, process, and structure unstructured medical data for analysis
• Research, evaluate, benchmark, and justify the selection of local LLMs for healthcare billing use cases
• Design and develop scalable LLM-driven analysis workflows running entirely on local infrastructure to ensure sensitive medical data remains secure
• Build supporting React interfaces for monitoring data ingestion, reviewing AI-generated recommendations, and visualizing analysis results
• Integrate AI services with existing healthcare management systems through REST APIs and MCP
• Collaborate directly with the client to gather requirements, validate AI outputs, and continuously improve solution quality
• Ensure reliability, reproducibility, performance, and auditability of AI-driven workflows
• Document model evaluations, benchmarking results, and architectural decisions
• Contribute to the overall system architecture and drive technical direction of the project

As a plus:

• Experience deploying and optimizing local LLMs on GPU infrastructure
• Experience with Gemma, MedGemma, Llama, Mistral, or other open-weight LLMs
• Experience with vector databases and Retrieval-Augmented Generation (RAG) architectures
• Previous experience in healthcare, healthtech, fintech, or other regulated industries handling sensitive data
• Experience building secure AI systems where data privacy is a key requirement
• Passion for clean code, experimentation, and delivering high-quality AI solutions