Jobs and Careers
NE
Senior AI Engineer – AI Services & LLM Integration
Ness Digital EngineeringIaşi, Romaniafull_timeVerifiedPosted 20 Jul 2025
About the role
Job id 6261Why NessWe know that people are our greatest asset. Our staff’s professionalism, innovation, teamwork, and dedication to excellence have helped us become one of the world’s leading technology companies. It is these qualities that are vital to our continued success. As a Ness employee, you will be working on products and platforms for some of the most innovative software companies in the world.You’ll gain knowledge working alongside other highly skilled professionals that will help accelerate your career progression. You’ll also benefit from an array of advantages like access to trainings and certifications, bonuses, and aids, socializing activities and attractive compensation.Requirements and responsibilitiesWe are looking for a Senior AI Engineer with deep experience in developing and deploying AI services and LLM-powered solutions. This role involves architecting scalable AI systems using tools like OpenAI APIs, Langflow, Qdrant, and observability tools like OpenTelemetry. You’ll work cross-functionally to create intelligent APIs, orchestrate AI pipelines, and enable real-time semantic search and decision-making capabilities in production environments.What you’ll do
- Design, develop, and deploy AI-powered services leveraging OpenAI, Langflow, and Qdrant for embedding search and vector retrieval.
- Create and orchestrate LLM workflows using Langflow or custom frameworks in Python.
- Integrate AI components with enterprise systems via robust Python APIs and services.
- Containerize AI solutions using Docker and manage scalable deployment pipelines.
- Implement monitoring and distributed tracing for AI workloads using OpenTelemetry.
- Automate build/test pipelines with PyBuilder and CI/CD tools.
- Lead architecture discussions around performance, latency, and prompt tuning.
- Ensure compliance, observability, and responsible AI practices throughout development.
- 10+ years of software engineering experience, including 3–5 years in AI/ML systems.
- Strong hands-on expertise in Python, AI service development, and API integration.
- Experience working with OpenAI APIs (ChatGPT, GPT-4, Embeddings, etc.) in production.
- Proficiency with Langflow for visual LLM orchestration and Qdrant for vector storage.
- Experience in containerization using Docker for AI workloads.
- Knowledge of OpenTelemetry for observability, logging, and tracing in microservices.
- Familiarity with PyBuilder, pytest, or other Python build/test frameworks.
What you’ll bring
- Experience with other vector DBs (e.g., Pinecone, Weaviate).
- Familiarity with stream processing and real-time event pipelines.
- Exposure to prompt engineering, RAG (Retrieval-Augmented Generation), and fine-tuning LLMs.
- Experience in deploying AI services on cloud platforms (AWS, GCP, Azure).
- Working knowledge of authentication, rate-limiting, and usage control in AI APIs.
Apply for this role
Generate a tailored application kit with a matched cover letter, interview prep, and CV highlights — in under 60 seconds.
Apply Now →Generate Application KitFree account required — sign up in 30s