AI Engineer

Neurithum — Nepal · Posted ~2 hours ago

Mid Full-time

Skills

Python FastAPI LLMs Machine Learning NLP Prompt Engineering RAG Vector Search Cloud Technologies LLM React Java Spring Boot

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary ✨ AI‑Generated

A growing technology team is seeking an AI Engineer to design and maintain intelligent backend services. The role focuses on building LLM-powered applications, retrieval pipelines, data extraction systems, and scalable APIs that transform complex information into actionable insights.

Highlights

Opportunity to build end-to-end AI systems that improve healthcare workflows, work on advanced machine learning solutions, and own impactful AI backend services.

Description

Neurithum is building AI-powered clinical software that transforms complex healthcare data into secure, actionable intelligence. Our platforms combine AI, LLMs, machine learning, NLP, and secure cloud technologies to improve clinical documentation, workflow automation, and decision-making. We are looking for an AI Engineer to own the AI layer end to end — from prompt engineering and retrieval pipelines to production FastAPI services that power clinician-facing applications such as Report Studio, our engine for generating structured clinical reports. What you'll doDesign, build, and maintain FastAPI-based AI backend services powering Report Studio and other AI features.Build LLM-powered features for clinical report generation, summarization, structured extraction, and analysis of EHR data.Develop and optimize prompt engineering, RAG pipelines, embeddings, and vector search to ground model outputs in real clinical data.Integrate AI services with our Java/Spring Boot backend and React frontend through clean, scalable REST APIs.Build evaluation harnesses to detect hallucinations, measure model quality, and prevent regressions before AI features reach clinicians.Train, evaluate, and deploy ML/NLP/neural network models for pattern recognition and clinical data analysis.Own production concerns including latency, cost, reliability, accuracy, and model performance.Work with cloud infrastructure, Docker, and scalable deployment practices.Collaborate with engineering, product, and clinical teams to translate healthcare requirements into robust AI solutions.Contribute to architecture decisions, technical documentation, monitoring, experimentation, and continuous improvement. What we're looking for3–4 years of hands-on experience building and shipping AI/ML systems.Strong Python skills with production experience in FastAPI or a comparable asynchronous framework.Practical experience with LLM APIs such as OpenAI, Anthropic, or similar providers.Strong understanding of prompt engineering, RAG architectures, embeddings, and vector search.Experience with vector databases such as pgvector, Pinecone, Weaviate, Chroma, or similar technologies.Solid foundations in NLP, machine learning, neural networks, and pattern recognition.Experience building and maintaining AI-powered SaaS applications.Working knowledge of Docker and deployment on AWS, GCP, Azure, or similar cloud platforms.Strong software engineering fundamentals, including clean code, APIs, data structures, algorithms, testing, and maintainable architecture.A strong bias toward measuring and improving model quality, not just integrating AI APIs.Ability to communicate technical concepts clearly and collaborate with cross-functional teams. Nice to haveExperience working with healthcare or clinical data.Familiarity with HL7, FHIR, EHR systems, HIPAA, or healthcare security and compliance requirements.Experience with LLM fine-tuning, LoRA/QLoRA, model distillation, or other model optimization techniques.Experience with MLOps, CI/CD, model monitoring, and production AI observability.Experience working with secure, regulated, or HIPAA-adjacent environments.Why Neurithum?You will work on real clinical AI systems, not just prototypes. You’ll have ownership across the AI stack — from experimentation and model evaluation to backend APIs and production deployment — while working on technology that directly improves healthcare workflows. Location: Remote · Nepal Employment: Full-time Experience: 3–4 years Interested? Apply through the application form linked in the post. https://forms.gle/dCyQQo5xuLhe4PH7A #AIEngineer #MachineLearning #LLM #Python #FastAPI #HealthTech #Hiring #RAG #NLP #HealthcareAI #NepalJobs #ArtificialIntelligence