AI Engineer at Avenga

Ренійська міська громада, Odesa Oblast, Ukraine -

Full Time

Start Date

Immediate

Expiry Date

04 May, 26

Salary

0.0

Posted On

03 Feb, 26

Experience

2 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

AI/ML, LLM-based Applications, Prompt Engineering, Agent Frameworks, RAG Implementation, Vector Databases, Semantic Search, Python, TypeScript, OpenAI APIs, Anthropic APIs, Azure OpenAI APIs, Agent Architectures, LLM Optimization, Clinical Environments, Benchmarking

Industry

IT Services and IT Consulting

Description

This is us At Avenga, we believe that human creativity empowers technology that matters. Operating globally, our 6000+ specialists provide a full spectrum of services, including business and tech advisory, enterprise solutions, CX, UX and Ul design, managed services, product development, and software development. This is the job The role is a technical leadership position focused on the design and development of business agents using the SADK framework. The specialist will apply advanced prompt engineering techniques and translate clinical operations requirements into scalable and compliant agent configurations. The position is highly hands-on, with more than 70% of responsibilities dedicated to active development. This is you 3+ years of experience in software engineering 3+ years of hands-on experience with AI/ML and LLM-based applications Strong expertise in prompt engineering and LLM application development Practical experience with OpenAI, Anthropic, or Azure OpenAI APIs Strong programming skills in Python and/or TypeScript Proven experience implementing RAG (Retrieval-Augmented Generation) solutions Hands-on experience with vector databases and semantic search Solid understanding of agent frameworks (e.g., LangChain, AutoGen, or similar) Experience evaluating, benchmarking, and optimizing LLM-powered systems This is your role Design and implement agent architectures (Knowledge, Review, Triage, Workflow, Research, Recommendation agents) Apply advanced prompt engineering techniques tailored to clinical and regulated environments Build and maintain RAG pipelines with knowledge base and vector database integrations Optimize agent performance across accuracy, latency, and cost dimensions Establish evaluation frameworks, quality metrics, and validation strategies for LLM-based agents Collaborate with domain analysts to translate clinical operations requirements into agent specifications Mentor AI/ML engineers and promote best practices in agent and LLM application development Partner with the Platform Pod to propose improvements to SADK and identify new MCP server needs Contribute hands-on to development tasks (70%+ coding involvement) What awaits you at Avenga? At Avenga, everyone matters. We provide equal opportunities in recruitment, career development, and leadership, regardless of race, ethnicity, gender identity, sexual orientation, disability, age, religion, or any other characteristic. We are committed to fostering a work environment where our diverse community of employees, candidates, and business partners actively shapes our growth. By bringing together people from different backgrounds and experiences, we build a workplace where everyone feels free to be themselves while honoring the boundaries of others.

Responsibilities

The role involves designing and implementing various agent architectures, such as Knowledge, Review, Triage, Workflow, Research, and Recommendation agents, while applying advanced prompt engineering techniques tailored for clinical and regulated environments. Responsibilities also include building and maintaining RAG pipelines, optimizing agent performance across accuracy, latency, and cost, and establishing evaluation frameworks for LLM-based agents.