emerchantpay is seeking to hire a Remote Senior AI Engineer in Sofia City Province, Bulgaria to help design, build, and roll out production-grade AI solutions, with a strong focus on AI engineering, AI agents, agentic workflows, machine learning, GenAI, and LLM-based applications. The role will have a strong focus on AWS, including Amazon Bedrock, Amazon Bedrock AgentCore, Amazon SageMaker, and other AWS AI/ML services.
Responsibilities
- Design, build, and maintain AI-powered applications, services, and integrations as part of the AI Engineering team.
- Implement solutions focused on AI agents, agentic workflows, automation, LLM-based applications, and AI-assisted business processes.
- Build and integrate AI applications using technologies such as Python (FastAPI/Flask/Django) or equivalent frameworks, React frontends, and relevant AI/ML frameworks.
- Implement AI solutions using AWS AI/ML services, including Amazon Bedrock, Amazon Bedrock AgentCore, Amazon SageMaker, and other AWS services for model hosting, inference, orchestration, data processing, monitoring, and security.
- Work closely with the AI Tech Lead to align on architecture, technology choices, engineering standards, AI patterns, and rollout approaches.
- Provide technical input and guidance to other engineers on AI implementation patterns, code quality, testing, observability, and production readiness.
- Develop and integrate AI agents that interact with internal APIs, business workflows, enterprise systems, knowledge bases, and external tools in a safe and controlled way.
- Build and maintain RAG-based solutions, including document ingestion, chunking, embeddings, vector search, retrieval logic, reranking, and grounding techniques.
- Support the development and deployment of machine learning models and AI solutions into production environments.
- Contribute to ML pipelines and MLOps practices, including data preparation, model training, experiment tracking, model deployment, monitoring, evaluation, and lifecycle management.
- Integrate LLMs through APIs.
- Implement AI evaluation approaches for LLM outputs, RAG quality, agent behavior, model performance, hallucination detection, safety, and reliability.
- Support prompt engineering, prompt versioning, function calling, tool use, memory patterns, guardrails, and LLM application testing.
- Design and consume APIs and contribute to cloud-based, scalable backend architectures.
- Collaborate with product managers, engineers, data scientists, DevOps, security, and business stakeholders to deliver practical AI solutions.
- Write clean, maintainable, testable, and well-documented code.
- Support production rollouts, troubleshooting, monitoring, optimization, and continuous improvement of AI systems.
- Stay current with modern AI technologies, frameworks, models, and engineering practices, and bring practical recommendations to the team.
Qualifications
- Minimum 7-8 years of professional experience in software engineering, AI engineering, ML engineering, data science, or related technical roles.
- At least 2-3 years of experience in AI development, ML engineering, or data science, with a demonstrated track record of deploying machine learning models and AI solutions in production environments.
- Strong hands-on experience building production-grade AI, ML, and data-driven systems.
- Practical experience with AI agents, agentic workflows, LLM-based applications, tool-calling architectures, workflow automation, and AI orchestration patterns.
- Strong understanding of modern AI concepts, including deep learning, generative AI, LLMs, embeddings, RAG, LLM fine-tuning, and AI evaluation.
- Strong Python development experience, including experience with Python (FastAPI/Flask/Django) or equivalent frameworks.
- Some experience with React for building user-facing AI tools, internal applications, dashboards, or workflow interfaces.
- Strong knowledge of AWS, including practical experience with cloud-native architectures, Amazon Bedrock, Amazon Bedrock AgentCore, Amazon SageMaker, and related AWS AI/ML services (the more, the better)
- Experience with advanced LLM frameworks such as LangChain, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, or similar agent/orchestration frameworks.
- Experience with PyTorch or TensorFlow, and familiarity with Hugging Face Transformers.
- Hands-on experience using LLMs via APIs, such as OpenAI, Anthropic, Gemini, or similar providers.
- Experience with ML pipelines and MLOps, including data preparation, model training, model deployment, experiment tracking, model/version management, monitoring, evaluation, and production support.
- Experience with AI evaluation frameworks, tools, and techniques for assessing LLM outputs, RAG performance, agent behavior, model quality, safety, reliability, and regression over time.
- Knowledge or practical experience with RLHF – human-in-the-loop evaluation, preference data, reward modeling, or feedback-driven model improvement.
- Experience with vector databases and retrieval/search technologies, such as Amazon OpenSearch, Pinecone, pgvector, or similar.
- Experience building RAG systems, including document ingestion, chunking strategies, embeddings, retrieval evaluation, reranking, and grounding techniques.
- Experience with model fine-tuning, embedding models, transformer architectures, open-source LLMs, and model benchmarking.
- Knowledge of API design, microservices, event-driven systems, and cloud-based architectures.
- Good understanding of security and governance requirements for AI systems, including access control, secrets management, data privacy, audit logging, and safe handling of sensitive data.
- Experience working in cross-functional teams with engineers, product managers, data scientists, DevOps, security, and business stakeholders.
- Strong problem-solving skills and ability to turn AI prototypes into reliable, maintainable production systems.
- Strong communication skills and ability to explain technical decisions clearly to both technical and non-technical stakeholders.
- Experience with Amazon Bedrock Agents, Amazon Bedrock Knowledge Bases, Amazon Bedrock Guardrails, or similar managed AI capabilities.
- Experience with containerization and orchestration, including Docker and EKS/ECS.
- Experience with infrastructure as code using Terraform, AWS CDK, or CloudFormation.
- Experience with data platforms, ETL/ELT pipelines, data lakes, feature stores, and real-time data processing.
- Experience implementing responsible AI controls, AI governance frameworks, safety guardrails, and compliance processes.
- Experience with observability for AI systems, including tracing, cost monitoring, prompt/model analytics, latency tracking, and quality dashboards.
- Experience integrating AI systems with enterprise platforms, internal APIs, CRM/ERP systems, ticketing systems, knowledge bases, and workflow engines.
- Contributions to open-source AI/ML projects, published technical content, conference talks, or patents in AI/ML-related areas.
- AWS certifications, especially in architecture, machine learning, security, or DevOps.
- Experience in fintech.
Benefits
- Fast-growing payment company;
- Excellent working conditions, casual atmosphere, and state-of-the-art hardware;
- Modern, challenging, constantly growing business;
- Professional development – books, trainings, certifications, etc.;
- Team buildings and fun activities;
- 25 days paid holiday, 1 day for every 2 years with us;
- Fully distributed and remote.
If you are interested, please apply with your CV in English only. Only short-listed candidates will be contacted.