AI Back End Engineer (LLM Specialist)

NEORIS, now part of EPAM, is a Digital Accelerator that helps companies step into the future, with more than 20 years of experience as Digital Partners of some of the world’s most important organizations. We are more than 4,000 professionals across 11 countries, with a multicultural and startup-driven culture that encourages innovation, continuous learning, and the creation of high-impact solutions for our clients. The final client must not be mentioned, even if it appears in the provided profile. No emojis or icons; the tone must remain corporate. If content is in English, keep it in English.

---

We are looking for: Senior AI Platform Backend Engineer (LLM)

---

Key Responsibilities:
• Design, implement, and manage cloud infrastructure on AWS using Infrastructure as Code (IaC) tools such as Terraform or AWS CloudFormation.
• Maintain and improve CI/CD pipelines using tools such as GitHub Actions, AWS CodePipeline, Jenkins, or ArgoCD.
• Implement and manage observability solutions like Amazon CloudWatch, Prometheus/Grafana, or ELK for monitoring and alerting.
• Support container orchestration environments such as EKS (Kubernetes), ECS, or Fargate.
• Develop backend architecture for AI Verification and Az ChatGPT Services using Python and FastAPI.
• Design and build solutions following Domain-Driven Design (DDD) and Test-Driven Development (TDD) best practices.
• Develop and maintain a LLM-as-a-judge production service for validating AI-generated content using HuggingFace, Transformers, SpaCy, NLTK, and BM25.
• Optimize model latency using compression techniques such as ONNX and quantization.
• Deploy and manage multi-service AI solutions on Kubernetes with Prometheus and Grafana monitoring.
• Build CI/CD pipelines for continuous integration and deployment of AI services.
• Design, build, and maintain high-load RAG solutions including ingestion services, message brokers, and retrieval services integrated as agent tools (LangChain, Unstructured, Azure OpenAI, Embeddings, Azure Cosmos DB, Azure Service Bus, Azure App Services).
• Perform prompt engineering using Chain-of-Thought, few-shot learning, and other techniques across multiple LLMs (OpenAI, Anthropic, Google).
• Research and evaluate agent-based solutions from different cloud vendors, including search APIs for LLMs, security aspects, and integration with modular architectures.

---

Requirements:

Mandatory:
• 5+ years of experience designing and implementing cloud solutions in AWS; experience with Azure is a strong plus.
• Proven background in building solutions involving IaaS, PaaS, Serverless, and distributed architectures.
• Advanced knowledge of Kubernetes, microservices, and IaC (Terraform).
• Hands-on experience with Machine Learning pipelines, MLOps, and LLM-based solutions (Chatbots, RAG).
• Strong experience developing in Python, including FastAPI.
• Experience with observability tools such as Prometheus, Grafana, ELK, or OpenTelemetry.
• Experience designing and deploying RAG systems and AI agent-based architectures.
• Strong understanding of CI/CD and DevOps practices.
• Experience deploying cloud-native services in AWS or Azure.
• Familiarity with model optimization and compression (ONNX, quantization).
• Experience in agile environments (Scrum).
• High level of English (C1 or equivalent).
• Proactive, results-oriented mindset.

Nice to Have:
• Experience with Cloud Security and compliance.
• Familiarity with cloud cost-optimization tools and automation frameworks.

---

What We Offer
• Permanent contract with a competitive salary
• Flexible work model with remote-work options
• Personalized career plan and continuous training (certifications, English, etc.)
• Participation in stable projects with strong technical components
• Flexible schedule with focus on work–life balance
• Social benefits tailored to your needs

You can learn more about us at http://www.neoris.com, or on Facebook, LinkedIn, Twitter, or Instagram: @NEORIS.
#LI-MM4