Senior AI Engineer
emerchantpay Ltd4 months ago
Remote, BulgariaSenior
Responsibilities
- Design, build, and maintain AI-powered applications, services, integrations, agents, agentic workflows, and LLM-based business solutions.
- Develop RAG systems involving document ingestion, chunking, embeddings, vector search, retrieval, reranking, and grounding.
- Implement and operate AI/ML solutions on AWS, including model hosting, inference, orchestration, data processing, monitoring, and security.
- Contribute to ML pipelines and MLOps practices covering data preparation, model training, experiment tracking, deployment, monitoring, evaluation, and lifecycle management.
- Integrate LLMs through APIs and implement prompt engineering, function calling, tool use, memory patterns, guardrails, and application testing.
- Develop evaluation methods for LLM outputs, RAG quality, agent behavior, model performance, hallucination detection, safety, and reliability.
- Design and consume APIs and contribute to scalable cloud-based backend architectures.
- Provide technical guidance to engineers and collaborate with technical, product, data, security, and business stakeholders.
- Support production rollouts, troubleshooting, monitoring, optimization, documentation, and continuous improvement of AI systems.
Requirements
- Requires 7–8 years of professional experience in software engineering, AI engineering, ML engineering, data science, or related technical roles.
- Requires 2–3 years of AI development, ML engineering, or data science experience and a track record of deploying machine learning models and AI solutions in production.
- Requires strong hands-on experience with production-grade AI, ML, and data-driven systems, including AI agents, agentic workflows, LLM applications, tool-calling architectures, and orchestration patterns.
- Requires knowledge of deep learning, generative AI, LLMs, embeddings, RAG, LLM fine-tuning, AI evaluation, model benchmarking, transformer architectures, and open-source LLMs.
- Requires strong Python development experience and experience with Python web frameworks such as FastAPI, Flask, or Django, plus some React experience.
- Requires strong AWS experience, including Amazon Bedrock, Amazon Bedrock AgentCore, Amazon SageMaker, and related AWS AI/ML services.
- Requires experience with agent and orchestration frameworks such as LangChain, LlamaIndex, Semantic Kernel, CrewAI, or AutoGen.
- Requires experience with PyTorch or TensorFlow, familiarity with Hugging Face Transformers, and LLM APIs such as OpenAI, Anthropic, or Gemini.
- Requires experience with ML pipelines, MLOps, AI evaluation, RLHF or human-in-the-loop model improvement, RAG systems, vector databases, retrieval technologies, and model fine-tuning.
- Requires knowledge of API design, microservices, event-driven and cloud-based architectures, and AI security and governance requirements.
- Experience with Amazon Bedrock Agents, Knowledge Bases, Guardrails, Docker, EKS, ECS, Terraform, AWS CDK, CloudFormation, data platforms, observability, responsible AI, enterprise integrations, open-source projects, technical publications, patents, AWS certifications, or fintech is advantageous.
- Requires strong problem-solving, cross-functional collaboration, and communication skills.
Benefits
- Fully distributed and remote workplace.
- 25 days of paid holiday, plus one additional day for every two years with the company.
- Professional development support including books, training, and certifications.
- Excellent working conditions, casual atmosphere, and state-of-the-art hardware.
- Team-building events and fun activities.
- Modern, challenging, and growing business environment.
Categories