Medior/Senior AI Engineer

SnapSoft is a leading AWS (Amazon Web Services) Premier Tier Partner specializing in cloud migrations, Generative AI (GenAI), DevOps, and application development. We help startups, SMEs, and enterprises drive innovation, reduce costs, and enhance security. Using our expertise, we seamlessly implement AI solutions, assist with migrations to AWS, and optimize DevOps process velocity. Our experienced team holds renowned AWS certifications, including the AWS Generative AI Competency, the Migration Acceleration Program, and the DevOps Competency. Through our scalable and secure applications, we are shaping the future of innovative technologies.

As an AI Engineer, you will design and implement Python-based generative AI (GenAI) services that combine Large Language Models (LLMs), retrieval and external systems into working automation.

You will join our Operations team, where we apply the same agentic process transformation internally that we deliver for our clients. Together with a Product Owner colleague, you will build SnapSoft's internal agentic portfolio, fed by needs from every department. The Product Owner collects the needs and outsources delivery where possible. You build in-house the solutions that involve sensitive data or system integrations. After the first year, you will move on to AI/ML client delivery projects.

What you'll be doing

• Design and build agentic systems that plan, call tools and automate real business workflows.

• Design and build multi-agent (agent-to-agent) solutions in which agents hand work to each other, review it and escalate to a human when needed.

• Develop LLM-powered applications, including RAG pipelines: chunking, embedding, retrieval strategies, evaluation and iteration.

• Work with vector databases and search: indexing strategies, hybrid and semantic search, relevance tuning.

• Integrate AI services with external systems through APIs: REST endpoints, authentication, webhooks, third-party and client-side SaaS platforms.

• Perform prompt engineering, model selection and systematic evaluation of LLM outputs.

• Build scalable Python services and the data flows behind them (ingestion, transformation, document preparation), including AI-driven data access such as Text2SQL.

• Deploy AI solutions on cloud infrastructure (e.g. on AWS: Bedrock, SageMaker, Lambda, Textract).

• Take solutions from POC and early feedback to production release, then prepare them for handover to operations.

• Align your architecture with the delivery team's existing platforms and standards, and work closely with them for technical guidance.
  

You are looking for us, if you have

• Bachelor's degree in Computer Science, Information Technology, or a related field, or equivalent practical experience.

• 3+ years of professional engineering experience, including recent hands-on work on GenAI projects. We care more about what you have actually built with GenAI than about how long your CV says "AI" on it. Software engineering, data engineering and data science backgrounds are all a strong starting point.

• Experience building AI agents: you have put at least one agentic solution into production that optimised, automated or replaced one or more business processes.

• Strong proficiency in Python and hands-on experience with the GenAI ecosystem (e.g. LangChain, LlamaIndex, agent frameworks, LLM provider SDKs, Pydantic).

• Solid understanding of LLM application concepts: RAG, embeddings, vector databases, tool calling, agent patterns, prompt engineering and evaluation.

• Proven experience designing, consuming and integrating APIs, and connecting AI services to existing systems.

• Hands-on experience deploying solutions on at least one major cloud platform (AWS, GCP, Azure or similar). AWS experience is a plus, not a requirement.

• Good command of SQL and a working understanding of core data engineering concepts (ETL, pipelines, data modelling).

• Excellent problem-solving and communication skills, and the ability to work independently and collaboratively in a fast-paced environment.

Nice to have

• Experience building multi-agent, agent-to-agent solutions.

• Experience with agent orchestration platforms (e.g. n8n or similar).

• Background in a professional services or IT services company.

• Real project experience with Amazon Bedrock AgentCore and the Strands Agents SDK.

• Classical machine learning and pre-LLM NLP experience, and the related toolkit (scikit-learn, pyspark, matplotlib).

• Computer vision, recommendation systems, anomaly detection experience.

• Experience with ETL processes and tools (e.g. Airflow, AWS Glue).

Do you see yourself in this role? Apply now!

If you're excited about this opportunity and believe you're the right fit, we'd love to hear from you!

Send us your CV.