About Jakala
We are Jakala — a data, AI and experience agency. Our team builds production-grade web applications and applied AI systems for enterprise clients in the healthcare and life sciences space. The work spans multi-agent LLM pipelines, retrieval-augmented generation, data connectors and the web applications that wrap them, delivered to clients who care deeply about accuracy, traceability and compliance.
We are looking for a Senior GenAI Developer focused on delivery — someone who turns a design into a working, reliable system and ships it. You'll be strong enough to take a small AI project or proof-of-concept and deliver it largely on your own, and equally comfortable working as part of a team on medium-to-large engagements. This is a hands-on senior individual-contributor role; the emphasis is on building.
How you'll work
You'll be part of a small agile pod working directly with the client — no layers in between. That means you hear the requirements first-hand, ask the questions yourself, show work in progress, and adjust as the client's thinking sharpens. It's a setup that suits people who like short feedback loops and a real say in what gets built, and who are curious enough about the client's world — how their business actually works, what their data means, what "correct" looks like to them — to build software that fits it.
What you’ll do
Build and ship. Develop production-grade web applications with AI integration — frontend, backend services and the APIs that connect them. Implement agent orchestration, RAG and semantic-search flows, document/data connectors, and the surrounding application logic.
Work directly with the client. Take requirements straight from the client, clarify what's ambiguous, propose options where the ask is open-ended, and demo what you've built. Turn conversations into working software and keep the client's expectations and the state of the system in sync.
Own delivery of smaller projects end to end. Take a PoC or small AI project from the agreed approach to a working, validated deliverable largely on your own — making sound implementation decisions as you go and flagging the ones that need input.
Contribute on larger teams. On medium-to-large projects, own your part of the system, integrate cleanly with other engineers, and keep your components reliable. Participate in technical discussions and contribute to implementation decisions within an agreed architecture.
Make AI systems reliable, not just demoable. Handle context windows, token and latency constraints, error and failure modes, and the accuracy/traceability requirements that matter in regulated work. Test what you build, including the behavior of the AI parts.
Integrate and connect. Design and consume REST APIs, integrate third-party AI models and enterprise data sources (external APIs, document ingestion, SharePoint and similar), and wire up authentication where needed.
Support the team. Review code, share patterns, and help teammates when needed.
What we’re looking for
Strong experience (5 years plus) building and shipping production software full-stack, with hands-on experience integrating LLMs into real applications (at least 1 year).
Solid LLM engineering skills: RAG, embeddings and vector search, prompt-engineering patterns, and at least some exposure to multi-agent orchestration. You understand how to make an AI feature behave reliably, not just produce a good first demo.
Backend: Python and/or Node.js.
Frontend: React, Next.js and/or Vue (component design, state management).
Data: SQL, NoSQL and vector databases.
Good understanding of REST APIs, integration patterns, Git and branching workflows.
Cloud familiarity with at least one major platform — AWS/Bedrock, GCP/Vertex AI or Azure/OpenAI — and the services that back AI workloads.
Comfort working directly with clients: gathering requirements first-hand, asking the awkward clarifying question early, explaining technical trade-offs to a non-t
