AI Engineer
Primary stack
Job description
About the Position
Your vision. Our solutions.
We are seeking an AI Engineer to design and implement systems that integrate models, data, and services for our cutting-edge intelligence solutions.
Responsibilities
-
Build AI Features & Agentic Workflows
- Implement multi-agent orchestration, retrieval pipelines, validator agents, and agent actions.
- Develop prompt templates, structured tools, and reasoning workflows aligned to pod requirements.
-
Retrieval, Vector Search & Data Pipelines
- Build and optimize vector search pipelines (FAISS, Milvus, Elasticsearch/OpenSearch, Pinecone, etc.).
- Implement retrieval strategies, embeddings, chunkers, ranking, and data-prep flows.
- Construct ETL/ELT pipelines supporting model and agent runtime.
-
Model Integration, Fine-Tuning & Evals
- Integrate LLMs (Azure OpenAI, Bedrock, Anthropic, etc.) into application workflows.
- Support lightweight fine-tuning, adapter models, or domain adaptation processes.
- Create evaluation suites (unit evals, behavioral tests, A/B experiments) for reliability and drift detection.
-
API, Backend & Product Integrations
- Develop and maintain API endpoints powering agent actions or retrieval layers.
- Integrate with application surfaces (web apps, dashboards, status surfaces, messaging interfaces).
- Work closely with UX/FE teams to ensure clean handoffs and stable data contracts.
-
Observability, Logging & Instrumentation
- Build instrumentation for latency, cost, error modes, and behavioral failures.
- Partner with AI Ops to support deployments, monitoring, and rollback.
- Ensure proper logging for audit trails, compliance, and troubleshooting.
-
Engineering Practices & SDLC Discipline
- Write clean, documented Python code with tests, linters, and version control discipline.
- Participate in code reviews, design reviews, and backlog refinement.
- Follow IE’s 12-week pod structure with predictable output each sprint.
Requirements
Technical Skills
- Strong Python engineering experience (3–6+ years).
- Experience with vector databases, embeddings, and retrieval systems.
- Hands-on experience building RAG, agentic workflows, or similar AI patterns.
- Familiarity with model evaluation, testing, and observability tools.
- Solid knowledge of APIs, microservices, and data-centric integrations.
- Comfort with cloud platforms (Azure, AWS, GCP) and CI/CD workflows.
Foundational Engineering Skills
- Excellent debugging, profiling, and performance optimization skills.
- Strong understanding of source control (Git), branching, PR reviews.
- Ability to work in structured agile environments with clear sprint increments.
Mindset
- High ownership, curiosity, and willingness to experiment.
- Loves hard problems and iterating on prototypes.
- Comfortable working in fast-changing frontier environments.
- Values clarity, structure, and quality in code.
We Offer
- Fully remote position with possible occasional in-person team sessions/workshops/gatherings (i.e., 1x quarter) likely to take place in Prague.
- Minimum 2-6pm CET overlap with preferred 2-7pm CET.
- Competitive salary and benefits package.
About the Company
The Workly s.r.o.
4D CENTER, Kodaňská 1441/46,
101 00, Praha 10.
Contact: [email protected]
Phone: + 420 775 371 991
©2023, All rights reserved.
© The Workly. This job description was sourced from the employer's public career page. TheJob is not the employer — we index the posting and route candidates to the source. All content rights and hiring decisions belong to the employer.
More at The Workly
All 265 rolesData Engineer/ Energy Trading Developer
The Workly · Germany
Project Manager for Calypso / Treasury Data Warehouse
The Workly · Austria
AWS Data Movement Engineer
The Workly · Prague
Senior Product Analyst
The Workly · Prague