About the role
We're growing our AI-driven capabilities and looking for an AI Engineer to design and deliver solutions that meet real business needs. You'll work closely with our engineering team and stakeholders across the business to understand what they need, then build, evaluate, and ship it.
What you'll do
Build new AI-driven solutions.
Translate business requirements into working systems, taking them from initial scoping through to production delivery.
Build agentic systems.
Design and ship LLM-powered agents that plan, call tools and APIs, and complete multi-step tasks with appropriate human oversight.
Integrate and orchestrate LLM-based workflows
using frameworks such as LangChain, CrewAI, or AutoGen.
Design AI-enabled workflows.
Map existing business processes, identify where AI adds real value, and build workflows that integrate with our internal systems and data.
Work end-to-end with LLMs.
Prompt design, context engineering, retrieval, tool integration, model selection, plus fine-tuning and adaptation of open-weight models where the use case justifies it.
Own evaluation.
Build eval datasets, automated test harnesses, and quality metrics so we can tell whether a change made the system better or worse.
Ship to production.
Deploy AI services with proper monitoring, tracing, logging, and cost/latency controls.
Design for safety.
Apply safeguards around data privacy, access control, prompt injection, and unsafe or incorrect outputs, especially for agents that can take real actions.
Raise the bar.
Contribute to our engineering standards for AI development through documentation, code review, and shared tooling.
Required qualifications
3+ years of professional software engineering experience, with at least 1 year building LLM-based applications that reached real users.
Strong Python skills, including experience with APIs, async programming, and testing.
Hands-on experience with
agentic AI
: tool/function calling, multi-step reasoning, orchestration frameworks (LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, the OpenAI Agents SDK, MCP, or similar), and an understanding of where agents break down.
Experience designing and implementing
RAG / retrieval pipelines
: chunking strategies, embeddings, vector and hybrid search, reranking.
Demonstrated ability to
evaluate
AI systems: building eval sets, LLM-as-judge and rule-based scoring, regression testing, and error analysis.
Clear communication with non-technical stakeholders, and the judgment to scope problems realistically.
Experience debugging non-deterministic systems: diagnosing intermittent failures where the same input doesn't always produce the same output.
Comfort deploying and operating services in production: version control, CI/CD, containers, and cloud infrastructure.
At least one AI project you've shipped and can walk us through in detail: what problem it solved, the technical choices you made, how you knew it worked, and what you'd do differently now.
Nice to have
Experience with microservices architecture and the
NestJS
framework (TypeScript/Node.js), for integrating AI services into our existing platform.
Experience self-hosting or serving open-weight models (vLLM, TGI, Ollama) and optimizing inference cost and latency.
Exposure to classical ML (classification, ranking, forecasting) and the judgment to reach for the simpler tool when an LLM isn't the right answer.
Data engineering background: pipelines, warehouses, data quality, and labeling workflows.
Experience with AI security topics such as prompt injection, jailbreak testing, red-teaming, and sandboxed tool execution.
How to apply
Send your resume to
[email protected]
, along with a link to or short description of an AI project you've built. It doesn't need to be production work is a plus but also personal projects and prototypes count, as long as you can explain the decisions behind them.
We're growing our AI-driven capabilities and looking for an AI Engineer to design and deliver solutions that meet real business needs. You'll work closely with our engineering team and stakeholders across the business to understand what they need, then build, evaluate, and ship it.
What you'll do
Build new AI-driven solutions.
Translate business requirements into working systems, taking them from initial scoping through to production delivery.
Build agentic systems.
Design and ship LLM-powered agents that plan, call tools and APIs, and complete multi-step tasks with appropriate human oversight.
Integrate and orchestrate LLM-based workflows
using frameworks such as LangChain, CrewAI, or AutoGen.
Design AI-enabled workflows.
Map existing business processes, identify where AI adds real value, and build workflows that integrate with our internal systems and data.
Work end-to-end with LLMs.
Prompt design, context engineering, retrieval, tool integration, model selection, plus fine-tuning and adaptation of open-weight models where the use case justifies it.
Own evaluation.
Build eval datasets, automated test harnesses, and quality metrics so we can tell whether a change made the system better or worse.
Ship to production.
Deploy AI services with proper monitoring, tracing, logging, and cost/latency controls.
Design for safety.
Apply safeguards around data privacy, access control, prompt injection, and unsafe or incorrect outputs, especially for agents that can take real actions.
Raise the bar.
Contribute to our engineering standards for AI development through documentation, code review, and shared tooling.
Required qualifications
3+ years of professional software engineering experience, with at least 1 year building LLM-based applications that reached real users.
Strong Python skills, including experience with APIs, async programming, and testing.
Hands-on experience with
agentic AI
: tool/function calling, multi-step reasoning, orchestration frameworks (LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, the OpenAI Agents SDK, MCP, or similar), and an understanding of where agents break down.
Experience designing and implementing
RAG / retrieval pipelines
: chunking strategies, embeddings, vector and hybrid search, reranking.
Demonstrated ability to
evaluate
AI systems: building eval sets, LLM-as-judge and rule-based scoring, regression testing, and error analysis.
Clear communication with non-technical stakeholders, and the judgment to scope problems realistically.
Experience debugging non-deterministic systems: diagnosing intermittent failures where the same input doesn't always produce the same output.
Comfort deploying and operating services in production: version control, CI/CD, containers, and cloud infrastructure.
At least one AI project you've shipped and can walk us through in detail: what problem it solved, the technical choices you made, how you knew it worked, and what you'd do differently now.
Nice to have
Experience with microservices architecture and the
NestJS
framework (TypeScript/Node.js), for integrating AI services into our existing platform.
Experience self-hosting or serving open-weight models (vLLM, TGI, Ollama) and optimizing inference cost and latency.
Exposure to classical ML (classification, ranking, forecasting) and the judgment to reach for the simpler tool when an LLM isn't the right answer.
Data engineering background: pipelines, warehouses, data quality, and labeling workflows.
Experience with AI security topics such as prompt injection, jailbreak testing, red-teaming, and sandboxed tool execution.
How to apply
Send your resume to
[email protected]
, along with a link to or short description of an AI project you've built. It doesn't need to be production work is a plus but also personal projects and prototypes count, as long as you can explain the decisions behind them.